Autorzy : Zbigniew Zhang Gan go Prawo ma Xiaofei Liu J. J. Johannes Hjorth Aleksander Kozłow Yutao He Szanghaj Zhang Jeanette Hellgren jako Kotaleski Yonghong Tian Sten Grillner Kai Du Tiejun Huang Autorzy : Zbigniew Zhang Gan go Prawo ma Xiaofei Liu reż. J. J. Johannes Hjorth Aleksander Kozłow Yutao He Szanghaj Zhang Jeanette Hellgren jako Kotaleski Yonghong Tian Sten Grillner Gdybyś Tiejun Huang Abstract Biophysically detailed multi-compartment models are powerful tools to explore computational principles of the brain and also serve as a theoretical framework to generate algorithms for artificial intelligence (AI) systems. However, the expensive computational cost severely limits the applications in both the neuroscience and AI fields. The major bottleneck during simulating detailed compartment models is the ability of a simulator to solve large systems of linear equations. Here, we present a novel endritic ierarchical cheduling (DHS) method to markedly accelerate such a process. We theoretically prove that the DHS implementation is computationally optimal and accurate. This GPU-based method performs with 2-3 orders of magnitude higher speed than that of the classic serial Hines method in the conventional CPU platform. We build a DeepDendrite framework, which integrates the DHS method and the GPU computing engine of the NEURON simulator and demonstrate applications of DeepDendrite in neuroscience tasks. We investigate how spatial patterns of spine inputs affect neuronal excitability in a detailed human pyramidal neuron model with 25,000 spines. Furthermore, we provide a brief discussion on the potential of DeepDendrite for AI, specifically highlighting its ability to enable the efficient training of biophysically detailed models in typical image classification tasks. D H S Introduction Deciphering the coding and computational principles of neurons is essential to neuroscience. Mammalian brains are composed of more than thousands of different types of neurons with unique morphological and biophysical properties. Even though it is no longer conceptually true, the “point-neuron” doctrine , in which neurons were regarded as simple summing units, is still widely applied in neural computation, especially in neural network analysis. In recent years, modern artificial intelligence (AI) has utilized this principle and developed powerful tools, such as artificial neural networks (ANN) . However, in addition to comprehensive computations at the single neuron level, subcellular compartments, such as neuronal dendrites, can also carry out nonlinear operations as independent computational units , , , , . Furthermore, dendritic spines, small protrusions that densely cover dendrites in spiny neurons, can compartmentalize synaptic signals, allowing them to be separated from their parent dendrites ex vivo and in vivo , , , . 1 2 3 4 5 6 7 8 9 10 11 Symulacje z wykorzystaniem biologicznie szczegółowych neuronów zapewniają teoretyczne ramy łączenia szczegółów biologicznych z zasadami obliczeniowymi. , allows us to model neurons with realistic dendritic morphologies, intrinsic ionic conductance, and extrinsic synaptic inputs. The backbone of the detailed multi-compartment model, i.e., dendrites, is built upon the classical Cable theory , which models the biophysical membrane properties of dendrites as passive cables, providing a mathematical description of how electronic signals invade and propagate throughout complex neuronal processes. By incorporating Cable theory with active biophysical mechanisms such as ion channels, excitatory and inhibitory synaptic currents, etc., a detailed multi-compartment model can achieve cellular and subcellular neuronal computations beyond experimental limitations , . 12 13 12 4 7 In addition to its profound impact on neuroscience, biologically detailed neuron models recently were utilized to bridge the gap between neuronal structural and biophysical details and AI. The prevailing technique in the modern AI field is ANNs consisting of point neurons, an analog to biological neural networks. Although ANNs with “backpropagation-of-error” (backprop) algorithm achieve remarkable performance in specialized applications, even beating top human professional players in the games of Go and chess , , the human brain still outperforms ANNs in domains that involve more dynamic and noisy environments , . Recent theoretical studies suggest that dendritic integration is crucial in generating efficient learning algorithms that potentially exceed backprop in parallel information processing , , . Furthermore, a single detailed multi-compartment model can learn network-level nonlinear computations for point neurons by adjusting only the synaptic strength , Wykazując pełny potencjał szczegółowych modeli w budowaniu bardziej potężnych systemów AI podobnych do mózgu. Dlatego priorytetem jest rozszerzenie paradygmatów w AI podobnej do mózgu od pojedynczych szczegółowych modeli neuronów do dużych sieci biologicznie szczegółowych. 14 15 16 17 18 19 20 21 22 One long-standing challenge of the detailed simulation approach lies in its exceedingly high computational cost, which has severely limited its application to neuroscience and AI. The major bottleneck of the simulation is to solve linear equations based on the foundational theories of detailed modeling , , . To improve efficiency, the classic Hines method reduces the time complexity for solving equations from O(n3) to O(n), which has been widely applied as the core algorithm in popular simulators such as NEURON and GENESIS . However, this method uses a serial approach to process each compartment sequentially. When a simulation involves multiple biophysically detailed dendrites with dendritic spines, the linear equation matrix (“Hines Matrix”) scales accordingly with an increasing number of dendrites or spines (Fig. ), making Hines method no longer practical, since it poses a very heavy burden on the entire simulation. 12 23 24 25 26 1e A reconstructed layer-5 pyramidal neuron model and the mathematical formula used with detailed neuron models. Workflow when numerically simulating detailed neuron models. The equation-solving phase is the bottleneck in the simulation. An example of linear equations in the simulation. Data dependency of the Hines method when solving linear equations in . The size of the Hines matrix scales with model complexity. The number of linear equations system to be solved undergoes a significant increase when models are growing more detailed. Computational cost (steps taken in the equation solving phase) of the serial Hines method on different types of neuron models. Illustration of different solving methods. Different parts of a neuron are assigned to multiple processing units in parallel methods (mid, right), shown with different colors. In the serial method (left), all compartments are computed with one unit. Computational cost of three methods in when solving equations of a pyramidal model with spines. Run time of different methods on solving equations for 500 pyramidal models with spines. The run time indicates the time consumption of 1 s simulation (solving the equation 40,000 times with a time step of 0.025 ms). p-Hines parallel method in CoreNEURON (on GPU), Branch based branch-based parallel method (on GPU), DHS Dendritic hierarchical scheduling method (on GPU). a b c d c e f g h g i During past decades, tremendous progress has been achieved to speed up the Hines method by using parallel methods at the cellular level, which enables to parallelize the computation of different parts in each cell , , , , , . However, current cellular-level parallel methods often lack an efficient parallelization strategy or lack sufficient numerical accuracy as compared to the original Hines method. 27 28 29 30 31 32 Here, we develop a fully automatic, numerically accurate, and optimized simulation tool that can significantly accelerate computation efficiency and reduce computational cost. In addition, this simulation tool can be seamlessly adopted for establishing and testing neural networks with biological details for machine learning and AI applications. Critically, we formulate the parallel computation of the Hines method as a mathematical scheduling problem and generate a Dendritic Hierarchical Scheduling (DHS) method based on combinatorial optimization and parallel computing theory . We demonstrate that our algorithm provides optimal scheduling without any loss of precision. Furthermore, we have optimized DHS for the currently most advanced GPU chip by leveraging the GPU memory hierarchy and memory accessing mechanisms. Together, DHS can speed up computation 60-1,500 times (Supplementary Table ) compared to the classic simulator NEURON while maintaining identical accuracy. 33 34 1 25 To enable detailed dendritic simulations for use in AI, we next establish the DeepDendrite framework by integrating the DHS-embedded CoreNEURON (an optimized compute engine for NEURON) platform jako silnik symulacyjny i dwa moduły pomocnicze (moduł I/O i moduł uczenia się) obsługujące algorytmy uczenia się dendrytu podczas symulacji. DeepDendrite działa na platformie sprzętowej GPU, obsługując zarówno regularne zadania symulacyjne w dziedzinie neuronaukowości, jak i zadania uczenia się w sztucznej inteligencji. 35 Last but not least, we also present several applications using DeepDendrite, targeting a few critical challenges in neuroscience and AI: (1) We demonstrate how spatial patterns of dendritic spine inputs affect neuronal activities with neurons containing spines throughout the dendritic trees (full-spine models). DeepDendrite enables us to explore neuronal computation in a simulated human pyramidal neuron model with ~25,000 dendritic spines. (2) In the discussion we also consider the potential of DeepDendrite in the context of AI, specifically, in creating ANNs with morphologically detailed human pyramidal neurons. Our findings suggest that DeepDendrite has the potential to drastically reduce the training duration, thus making detailed network models more feasible for data-driven tasks. All source code for DeepDendrite, the full-spine models and the detailed dendritic network model are publicly available online (see Code Availability). Our open-source learning framework can be readily integrated with other dendritic learning rules, such as learning rules for nonlinear (full-active) dendrites Burst-dependentne plastyczność synaptyczna , and learning with spike prediction . Overall, our study provides a complete set of tools that have the potential to change the current computational neuroscience community ecosystem. By leveraging the power of GPU computing, we envision that these tools will facilitate system-level explorations of computational principles of the brain’s fine structures, as well as promote the interaction between neuroscience and modern AI. 21 20 36 Results Dendritic Hierarchical Scheduling (DHS) method Obliczanie prądów jonowych i rozwiązywanie równań liniowych są dwoma krytycznymi fazami podczas symulacji neuronów biofizycznie szczegółowych, które są czasochłonne i stanowią poważne obciążenia obliczeniowe.Na szczęście obliczanie prądów jonowych każdego oddziału jest całkowicie niezależnym procesem, dzięki czemu może być naturalnie równolegle na urządzeniach z masywnymi równoległymi jednostkami obliczeniowymi, takimi jak GPU . As a consequence, solving linear equations becomes the remaining bottleneck for the parallelization process (Fig. ). 37 1a–f Aby rozwiązać ten problem, opracowano metody równoległe na poziomie komórkowym, które przyspieszają obliczenia pojedynczych komórek, „podzielając” pojedynczą komórkę na kilka komórek, które można obliczyć równolegle. , , Jednak takie metody w dużej mierze opierają się na uprzedniej wiedzy, aby wygenerować praktyczne strategie, jak podzielić pojedynczy neuron na oddziały (Rys. ; Supplementary Fig. ). Hence, it becomes less efficient for neurons with asymmetrical morphologies, e.g., pyramidal neurons and Purkinje neurons. 27 28 38 1g i 1 Naszym celem jest opracowanie bardziej wydajnej i precyzyjnej metody równoległej do symulacji biologicznie szczegółowych sieci neuronowych. Po pierwsze, ustalamy kryteria dla dokładności metody równoległej na poziomie komórkowym. , we propose three conditions to make sure a parallel method will yield identical solutions as the serial computing Hines method according to the data dependency in the Hines method (see Methods). Then to theoretically evaluate the run time, i.e., efficiency, of the serial and parallel computing methods, we introduce and formulate the concept of computational cost as the number of steps a method takes in solving equations (see Methods). 34 Based on the simulation accuracy and computational cost, we formulate the parallelization problem as a mathematical scheduling problem (see Methods). In simple terms, we view a single neuron as a tree with many nodes (compartments). For parallel threads, we can compute at most nodes at each step, but we need to ensure a node is computed only if all its children nodes have been processed; our goal is to find a strategy with the minimum number of steps for the entire procedure. k k To generate an optimal partition, we propose a method called Dendritic Hierarchical Scheduling (DHS) (theoretical proof is presented in the Methods). The key idea of DHS is to prioritize deep nodes (Fig. ), which results in a hierarchical schedule order. The DHS method includes two steps: analyzing dendritic topology and finding the best partition: (1) Given a detailed model, we first obtain its corresponding dependency tree and calculate the depth of each node (the depth of a node is the number of its ancestor nodes) on the tree (Fig. ). (2) After topology analysis, we search the candidates and pick at most deepest candidate nodes (a node is a candidate only if all its children nodes have been processed). This procedure repeats until all nodes are processed (Fig. ). 2a 2b, c k 2d DHS work flow. DHS processes deepest candidate nodes each iteration. Ilustracja obliczania głębokości węzła modelu oddziałowego. Model jest najpierw przekształcony w strukturę drzewa, a następnie obliczana jest głębokość każdego węzła. Topology analysis on different neuron models. Six neurons with distinct morphologies are shown here. For each model, the soma is selected as the root of the tree so the depth of the node increases from the soma (0) to the distal dendrites. Illustration of performing DHS on the model in with four threads. Candidates: nodes that can be processed. Selected candidates: nodes that are picked by DHS, i.e., the deepest candidates. Processed nodes: nodes that have been processed before. Parallelization strategy obtained by DHS after the process in . Each node is assigned to one of the four parallel threads. DHS reduces the steps of serial node processing from 14 to 5 by distributing nodes to multiple threads. Relative cost, i.e., the proportion of the computational cost of DHS to that of the serial Hines method, when applying DHS with different numbers of threads on different types of models. a k b c d b k e d f Take a simplified model with 15 compartments as an example, using the serial computing Hines method, it takes 14 steps to process all nodes, while using DHS with four parallel units can partition its nodes into five subsets (Fig. ): {{9,10,12,14}, {1,7,11,13}, {2,3,4,8}, {6}, {5}}. Because nodes in the same subset can be processed in parallel, it takes only five steps to process all nodes using DHS (Fig. ). 2d 2e Next, we apply the DHS method on six representative detailed neuron models (selected from ModelDB ) z różną liczbą dróg (Fig. ):, including cortical and hippocampal pyramidal neurons , , , cerebellar Purkinje neurons , striatal projection neurons (SPN ), and olfactory bulb mitral cells , covering the major principal neurons in sensory, cortical and subcortical areas. We then measured the computational cost. The relative computational cost here is defined by the proportion of the computational cost of DHS to that of the serial Hines method. The computational cost, i.e., the number of steps taken in solving equations, drops dramatically with increasing thread numbers. For example, with 16 threads, the computational cost of DHS is 7%-10% as compared to the serial Hines method. Intriguingly, the DHS method reaches the lower bounds of their computational cost for presented neurons when given 16 or even 8 parallel threads (Fig. ), suggesting adding more threads does not improve performance further because of the dependencies between compartments. 39 2f 40 41 42 43 44 45 2f Together, we generate a DHS method that enables automated analysis of the dendritic topology and optimal partition for parallel computing. It is worth noting that DHS finds the optimal partition before the simulation starts, and no extra computation is needed to solve equations. Speeding up DHS by GPU memory boosting DHS computes each neuron with multiple threads, which consumes a vast amount of threads when running neural network simulations. Graphics Processing Units (GPUs) consist of massive processing units (i.e., streaming processors, SPs, Fig. ) for parallel computing . In theory, many SPs on the GPU should support efficient simulation for large-scale neural networks (Fig. ). However, we consistently observed that the efficiency of DHS significantly decreased when the network size grew, which might result from scattered data storage or extra memory access caused by loading and writing intermediate results (Fig. , left). 3a, b 46 3c 3d GPU architecture and its memory hierarchy. Each GPU contains massive processing units (stream processors). Different types of memory have different throughput. Architektura strumieniowych multiprocesorów (SM). Każdy SM zawiera wiele procesorów strumieniowych, rejestrów i pamięci podręcznej L1. Applying DHS on two neurons, each with four threads. During simulation, each thread executes on one stream processor. Memory optimization strategy on GPU. Top panel, thread assignment and data storage of DHS, before (left) and after (right) memory boosting. Bottom, an example of a single step in triangularization when simulating two neurons in . Processors send a data request to load data for each thread from global memory. Without memory boosting (left), it takes seven transactions to load all request data and some extra transactions for intermediate results. With memory boosting (right), it takes only two transactions to load all request data, registers are used for intermediate results, which further improve memory throughput. Run time of DHS (32 threads each cell) with and without memory boosting on multiple layer 5 pyramidal models with spines. Przyspieszenie wzrostu pamięci na wielowarstwowych modelach piramidalnych o 5 warstwach z pętlami. a b c d d e f We solve this problem by GPU memory boosting, a method to increase memory throughput by leveraging GPU’s memory hierarchy and access mechanism. Based on the memory loading mechanism of GPU, successive threads loading aligned and successively-stored data lead to a high memory throughput compared to accessing scatter-stored data, which reduces memory throughput , . To achieve high throughput, we first align the computing orders of nodes and rearrange threads according to the number of nodes on them. Then we permute data storage in global memory, consistent with computing orders, i.e., nodes that are processed at the same step are stored successively in global memory. Moreover, we use GPU registers to store intermediate results, further strengthening memory throughput. The example shows that memory boosting takes only two memory transactions to load eight request data (Fig. , right). Furthermore, experiments on multiple numbers of pyramidal neurons with spines and the typical neuron models (Fig. ; Supplementary Fig. ) show that memory boosting achieves a 1.2-3.8 times speedup as compared to the naïve DHS. 46 47 3d 3e, f 2 To comprehensively test the performance of DHS with GPU memory boosting, we select six typical neuron models and evaluate the run time of solving cable equations on massive numbers of each model (Fig. ). We examined DHS with four threads (DHS-4) and sixteen threads (DHS-16) for each neuron, respectively. Compared to the GPU method in CoreNEURON, DHS-4 and DHS-16 can speed up about 5 and 15 times, respectively (Fig. ). Moreover, compared to the conventional serial Hines method in NEURON running with a single-thread of CPU, DHS speeds up the simulation by 2-3 orders of magnitude (Supplementary Fig. ), while retaining the identical numerical accuracy in the presence of dense spines (Supplementary Figs. and ), active dendrites (Supplementary Fig. ) and different segmentation strategies (Supplementary Fig. ). 4 4a 3 4 8 7 7 Czas biegu rozwiązywania równań dla symulacji 1 s na GPU (dt = 0,025 ms, 40 000 iteracji w sumie). CoreNEURON: metoda równoległa stosowana w CoreNEURON; DHS-4: DHS z czterema pasmami dla każdego neuronu; DHS-16: DHS z 16 pasmami dla każdego neuronu. , Visualization of the partition by DHS-4 and DHS-16, each color indicates a single thread. During computation, each thread switches among different branches. a b c DHS tworzy optymalne partycjonowanie specyficzne dla typu komórki To gain insights into the working mechanism of the DHS method, we visualized the partitioning process by mapping compartments to each thread (every color presents a single thread in Fig. ). The visualization shows that a single thread frequently switches among different branches (Fig. ). Interestingly, DHS generates aligned partitions in morphologically symmetric neurons such as the striatal projection neuron (SPN) and the Mitral cell (Fig. ). By contrast, it generates fragmented partitions of morphologically asymmetric neurons like the pyramidal neurons and Purkinje cell (Fig. ), indicating that DHS splits the neural tree at individual compartment scale (i.e., tree node) rather than branch scale. This cell-type-specific fine-grained partition enables DHS to fully exploit all available threads. 4b, c 4b, C 4b, C 4b, C Podsumowując, DHS i zwiększanie pamięci generują teoretycznie udowodnione optymalne rozwiązanie do rozwiązywania równań liniowych równolegle z bezprecedensową wydajnością. Korzystając z tej zasady, zbudowaliśmy platformę DeepDendrite o otwartym dostępie, którą neurolodzy mogą wykorzystać do wdrażania modeli bez jakiejkolwiek specyficznej wiedzy z zakresu programowania GPU. Poniżej pokazujemy, jak możemy wykorzystać DeepDendrite w zadaniach neuronaukowych. DHS enables spine-level modelling As dendritic spines receive most of the excitatory input to cortical and hippocampal pyramidal neurons, striatal projection neurons, etc., their morphologies and plasticity are crucial for regulating neuronal excitability , , , , . However, spines are too small ( ~ 1 μm length) to be directly measured experimentally with regard to voltage-dependent processes. Thus, theoretical work is critical for the full understanding of the spine computations. 10 48 49 50 51 We can model a single spine with two compartments: the spine head where synapses are located and the spine neck that links the spine head to dendrites . The theory predicts that the very thin spine neck (0.1-0.5 um in diameter) electronically isolates the spine head from its parent dendrite, thus compartmentalizing the signals generated at the spine head . However, the detailed model with fully distributed spines on dendrites (“full-spine model”) is computationally very expensive. A common compromising solution is to modify the capacitance and resistance of the membrane by a spine factor , instead of modeling all spines explicitly. Here, the spine factor aims at approximating the spine effect on the biophysical properties of the cell membrane . 52 53 F 54 F 54 Inspired by the previous work of Eyal et al. Badaliśmy, w jaki sposób różne wzorce przestrzenne wchodów pobudzających utworzone na kręgowcach dendrytowych kształtują aktywność neuronalną w modelu ludzkiego neuronu piramidalnego z wyraźnie modelowanymi kręgowcami (Rys. ). Noticeably, Eyal et al. employed the spine factor to incorporate spines into dendrites while only a few activated spines were explicitly attached to dendrites (“few-spine model” in Fig. 2) Wartość spine in their model was computed from the dendritic area and spine area in the reconstructed data. Accordingly, we calculated the spine density from their reconstructed data to make our full-spine model more consistent with Eyal’s few-spine model. With the spine density set to 1.3 μm-1, the pyramidal neuron model contained about 25,000 spines without altering the model’s original morphological and biophysical properties. Further, we repeated the previous experiment protocols with both full-spine and few-spine models. We use the same synaptic input as in Eyal’s work but attach extra background noise to each sample. By comparing the somatic traces (Fig. ) and spike probability (Fig. ) in full-spine and few-spine models, we found that the full-spine model is much leakier than the few-spine model. In addition, the spike probability triggered by the activation of clustered spines appeared to be more nonlinear in the full-spine model (the solid blue line in Fig. ) than in the few-spine model (the dashed blue line in Fig. ). These results indicate that the conventional F-factor method may underestimate the impact of dense spine on the computations of dendritic excitability and nonlinearity. 51 5a F 5a F 5b, c 5d 5d 5d Experiment setup. We examine two major types of models: few-spine models and full-spine models. Few-spine models (two on the left) are the models that incorporated spine area globally into dendrites and only attach individual spines together with activated synapses. In full-spine models (two on the right), all spines are explicitly attached over whole dendrites. We explore the effects of clustered and randomly distributed synaptic inputs on the few-spine models and the full-spine models, respectively. Somatic voltages recorded for cases in . Colors of the voltage curves correspond to , scale bar: 20 ms, 20 mV. Color-coded voltages during the simulation in at specific times. Colors indicate the magnitude of voltage. Somatic spike probability as a function of the number of simultaneously activated synapses (as in Eyal et al.’s work) for four cases in . Background noise is attached. Run time of experiments in with different simulation methods. NEURON: conventional NEURON simulator running on a single CPU core. CoreNEURON: CoreNEURON simulator on a single GPU. DeepDendrite: DeepDendrite on a single GPU. a b a a c b d a e d In the DeepDendrite platform, both full-spine and few-spine models achieved 8 times speedup compared to CoreNEURON on the GPU platform and 100 times speedup compared to serial NEURON on the CPU platform (Fig. ; Supplementary Table ) while keeping the identical simulation results (Supplementary Figs. and ). Therefore, the DHS method enables explorations of dendritic excitability under more realistic anatomic conditions. 5e 1 4 8 Discussion In this work, we propose the DHS method to parallelize the computation of Hines method and we mathematically demonstrate that the DHS provides an optimal solution without any loss of precision. Next, we implement DHS on the GPU hardware platform and use GPU memory boosting techniques to refine the DHS (Fig. ). When simulating a large number of neurons with complex morphologies, DHS with memory boosting achieves a 15-fold speedup (Supplementary Table ) as compared to the GPU method used in CoreNEURON and up to 1,500-fold speedup compared to serial Hines method in the CPU platform (Fig. ; Supplementary Fig. and Supplementary Table ). Furthermore, we develop the GPU-based DeepDendrite framework by integrating DHS into CoreNEURON. Finally, as a demonstration of the capacity of DeepDendrite, we present a representative application: examine spine computations in a detailed pyramidal neuron model with 25,000 spines. Further in this section, we elaborate on how we have expanded the DeepDendrite framework to enable efficient training of biophysically detailed neural networks. To explore the hypothesis that dendrites improve robustness against adversarial attacks Pokazujemy, że DeepDendrite może obsługiwać zarówno symulacje neuronaukowe, jak i związane z sztuczną inteligencją szczegółowe zadania sieciowe z niespotykaną prędkością, co znacząco promuje szczegółowe symulacje neuronaukowe i potencjalnie dla przyszłych eksploracji sztucznej inteligencji. 55 3 1 4 3 1 56 Decades of efforts have been invested in speeding up the Hines method with parallel methods. Early work mainly focuses on network-level parallelization. In network simulations, each cell independently solves its corresponding linear equations with the Hines method. Network-level parallel methods distribute a network on multiple threads and parallelize the computation of each cell group with each thread , . With network-level methods, we can simulate detailed networks on clusters or supercomputers W ostatnich latach, GPU został użyty do szczegółowej symulacji sieci.Ponieważ GPU zawiera masywne jednostki obliczeniowe, jeden pasek jest zwykle przypisywany do jednej komórki, a nie do grupy komórek , , Dzięki dalszej optymalizacji metody oparte na GPU osiągają znacznie wyższą wydajność w symulacji sieci. Jednak obliczenia wewnątrz komórek są nadal seryjne w metodach na poziomie sieci, więc nadal nie mogą poradzić sobie z problemem, gdy „matryca Hines” każdej komórki jest duża. 57 58 59 35 60 61 Cellular-level parallel methods further parallelize the computation inside each cell. The main idea of cellular-level parallel methods is to split each cell into several sub-blocks and parallelize the computation of those sub-blocks , Jednak typowe metody na poziomie komórkowym (np. metoda „multi-split” ) pay less attention to the parallelization strategy. The lack of a fine parallelization strategy results in unsatisfactory performance. To achieve higher efficiency, some studies try to obtain finer-grained parallelization by introducing extra computation operations , , or making approximations on some crucial compartments, while solving linear equations , . These finer-grained parallelization strategies can get higher efficiency but lack sufficient numerical accuracy as in the original Hines method. 27 28 28 29 38 62 63 64 Unlike previous methods, DHS adopts the finest-grained parallelization strategy, i.e., compartment-level parallelization. By modeling the problem of “how to parallelize” as a combinatorial optimization problem, DHS provides an optimal compartment-level parallelization strategy. Moreover, DHS does not introduce any extra operation or value approximation, so it achieves the lowest computational cost and retains sufficient numerical accuracy as in the original Hines method at the same time. Dendritic spines are the most abundant microstructures in the brain for projection neurons in the cortex, hippocampus, cerebellum, and basal ganglia. As spines receive most of the excitatory inputs in the central nervous system, electrical signals generated by spines are the main driving force for large-scale neuronal activities in the forebrain and cerebellum , . The structure of the spine, with an enlarged spine head and a very thin spine neck—leads to surprisingly high input impedance at the spine head, which could be up to 500 MΩ, combining experimental data and the detailed compartment modeling approach , . Due to such high input impedance, a single synaptic input can evoke a “gigantic” EPSP ( ~ 20 mV) at the spine-head level , W ten sposób zwiększa prądy NMDA i prądy kanałów jonowych w kręgosłupie. Jednak w klasycznych pojedynczych szczegółowych modelach komor, wszystkie pętle są zastępowane przez coefficient modifying the dendritic cable geometries . This approach may compensate for the leak currents and capacitance currents for spines. Still, it cannot reproduce the high input impedance at the spine head, which may weaken excitatory synaptic inputs, particularly NMDA currents, thereby reducing the nonlinearity in the neuron’s input-output curve. Our modeling results are in line with this interpretation. 10 11 48 65 48 66 11 F 54 On the other hand, the spine’s electrical compartmentalization is always accompanied by the biochemical compartmentalization , , , co skutkuje drastycznym wzrostem wewnętrznego [Ca2+], w kręgosłupie i kaskadą procesów molekularnych obejmujących plastyczność synaptyczną o znaczeniu dla uczenia się i pamięci. intrygująco, proces biochemiczny wywołany przez uczenie się, z kolei, przekształca morfologię kręgosłupa, powiększając (lub zwężając) głowę kręgosłupa lub wydłużając (lub skracając) szyję kręgosłupa, co znacząco zmienia zdolność elektryczną kręgosłupa , , , . Such experience-dependent changes in spine morphology also referred to as “structural plasticity”, have been widely observed in the visual cortex , , somatosensory cortex , , motor cortex , hippocampus i ganglionu bazalnego in vivo. They play a critical role in motor and spatial learning as well as memory formation. However, due to the computational costs, nearly all detailed network models exploit the “F-factor” approach to replace actual spines, and are thus unable to explore the spine functions at the system level. By taking advantage of our framework and the GPU platform, we can run a few thousand detailed neurons models, each with tens of thousands of spines on a single GPU, while maintaining ~100 times faster than the traditional serial method on a single CPU (Fig. ). Therefore, it enables us to explore of structural plasticity in large-scale circuit models across diverse brain regions. 8 52 67 67 68 69 70 71 72 73 74 75 9 76 5e Another critical issue is how to link dendrites to brain functions at the systems/network level. It has been well established that dendrites can perform comprehensive computations on synaptic inputs due to enriched ion channels and local biophysical membrane properties , , . For example, cortical pyramidal neurons can carry out sublinear synaptic integration at the proximal dendrite but progressively shift to supralinear integration at the distal dendrite . Moreover, distal dendrites can produce regenerative events such as dendritic sodium spikes, calcium spikes, and NMDA spikes/plateau potentials , . Such dendritic events are widely observed in mice or even human cortical neurons in vitro, which may offer various logical operations , or gating functions , . Recently, in vivo recordings in awake or behaving mice provide strong evidence that dendritic spikes/plateau potentials are crucial for orientation selectivity in the visual cortex , sensory-motor integration in the whisker system , , and spatial navigation in the hippocampal CA1 region . 5 6 7 77 6 78 6 79 6 79 80 81 82 83 84 85 To establish the causal link between dendrites and animal (including human) patterns of behavior, large-scale biophysically detailed neural circuit models are a powerful computational tool to realize this mission. However, running a large-scale detailed circuit model of 10,000-100,000 neurons generally requires the computing power of supercomputers. It is even more challenging to optimize such models for in vivo data, as it needs iterative simulations of the models. The DeepDendrite framework can directly support many state-of-the-art large-scale circuit models , , , which were initially developed based on NEURON. Moreover, using our framework, a single GPU card such as Tesla A100 could easily support the operation of detailed circuit models of up to 10,000 neurons, thereby providing carbon-efficient and affordable plans for ordinary labs to develop and optimize their own large-scale detailed models. 86 87 88 Ostatnie prace nad odkryciem ról dendrytycznych w nauce specyficznej dla zadań osiągnęły niezwykłe rezultaty w dwóch kierunkach, tj. rozwiązywanie trudnych zadań, takich jak zestaw danych klasyfikacji obrazów ImageNet z uproszczonymi sieciami dendrytycznymi. , i odkrywanie pełnego potencjału uczenia się na bardziej realistycznych neuronach , Jednak istnieje kompromis między wielkością modelu a szczegółami biologicznymi, ponieważ wzrost skali sieci jest często poświęcony na złożoność na poziomie neuronów. , , . Moreover, more detailed neuron models are less mathematically tractable and computationally expensive . 20 21 22 19 20 89 21 There has also been progress in the role of active dendrites in ANNs for computer vision tasks. Iyer et al. . proposed a novel ANN architecture with active dendrites, demonstrating competitive results in multi-task and continual learning. Jones and Kording used a binary tree to approximate dendrite branching and provided valuable insights into the influence of tree structure on single neurons’ computational capacity. Bird et al. . proposed a dendritic normalization rule based on biophysical behavior, offering an interesting perspective on the contribution of dendritic arbor structure to computation. While these studies offer valuable insights, they primarily rely on abstractions derived from spatially extended neurons, and do not fully exploit the detailed biological properties and spatial information of dendrites. Further investigation is needed to unveil the potential of leveraging more realistic neuron models for understanding the shared mechanisms underlying brain computation and deep learning. 90 91 92 W odpowiedzi na te wyzwania opracowaliśmy DeepDendrite, narzędzie, które wykorzystuje metodę Dendritic Hierarchical Scheduling (DHS) do znacznego obniżenia kosztów obliczeniowych i zawiera moduł I/O i moduł uczenia się do obsługi dużych zbiorów danych. ). This network demonstrated efficient training capabilities in image classification tasks, achieving approximately 25 times speedup compared to training on a traditional CPU-based platform (Fig. • stół dodatkowy ). 6a, b 6f 1 The illustration of the Human Pyramidal Cell Network (HPC-Net) for image classification. Images are transformed to spike trains and fed into the network model. Learning is triggered by error signals propagated from soma to dendrites. Training with mini-batch. Multiple networks are simulated simultaneously with different images as inputs. The total weight updates ΔW are computed as the average of ΔWi from each network. Porównanie HPC-Net przed i po treningu. Po lewej, wizualizacja odpowiedzi ukrytych neuronów na określony wkład przed (górą) i po (spodzie) treningu. Prawy, ukryty ciężar warstwy (od wejścia do ukrytej warstwy) dystrybucji przed (górą) i po (spodzie) treningu. Workflow of the transfer adversarial attack experiment. We first generate adversarial samples of the test set on a 20-layer ResNet. Then use these adversarial samples (noisy images) to test the classification accuracy of models trained with clean images. Prediction accuracy of each model on adversarial samples after training 30 epochs on MNIST (left) and Fashion-MNIST (right) datasets. Run time of training and testing for the HPC-Net. The batch size is set to 16. Left, run time of training one epoch. Right, run time of testing. Parallel NEURON + Python: training and testing on a single CPU with multiple cores, using 40-process-parallel NEURON to simulate the HPC-Net and extra Python code to support mini-batch training. DeepDendrite: training and testing the HPC-Net on a single GPU with DeepDendrite. a b c d e f Additionally, it is widely recognized that the performance of Artificial Neural Networks (ANNs) can be undermined by adversarial attacks —intentionally engineered perturbations devised to mislead ANNs. Intriguingly, an existing hypothesis suggests that dendrites and synapses may innately defend against such attacks . Our experimental results utilizing HPC-Net lend support to this hypothesis, as we observed that networks endowed with detailed dendritic structures demonstrated some increased resilience to transfer adversarial attacks compared to standard ANNs, as evident in MNIST and Fashion-MNIST Zbiór danych (Fig. ). This evidence implies that the inherent biophysical properties of dendrites could be pivotal in augmenting the robustness of ANNs against adversarial interference. Nonetheless, it is essential to conduct further studies to validate these findings using more challenging datasets such as ImageNet . 93 56 94 95 96 6d, e 97 In conclusion, DeepDendrite has shown remarkable potential in image classification tasks, opening up a world of exciting future directions and possibilities. To further advance DeepDendrite and the application of biologically detailed dendritic models in AI tasks, we may focus on developing multi-GPU systems and exploring applications in other domains, such as Natural Language Processing (NLP), where dendritic filtering properties align well with the inherently noisy and ambiguous nature of human language. Challenges include testing scalability in larger-scale problems, understanding performance across various tasks and domains, and addressing the computational complexity introduced by novel biological principles, such as active dendrites. By overcoming these limitations, we can further advance the understanding and capabilities of biophysically detailed dendritic neural networks, potentially uncovering new advantages, enhancing their robustness against adversarial attacks and noisy inputs, and ultimately bridging the gap between neuroscience and modern AI. Methods Simulation with DHS CoreNEURON simulator ( ) uses the NEURON architecture and is optimized for both memory usage and computational speed. We implement our Dendritic Hierarchical Scheduling (DHS) method in the CoreNEURON environment by modifying its source code. All models that can be simulated on GPU with CoreNEURON can also be simulated with DHS by executing the following command: 35 https://github.com/BlueBrain/CoreNeuron 25 coreneuron_exec -d /path/to/models -e time --cell-permute 3 --cell-nthread 16 --gpu The usage options are as in Table . 1 Accuracy of the simulation using cellular-level parallel computation To ensure the accuracy of the simulation, we first need to define the correctness of a cellular-level parallel algorithm to judge whether it will generate identical solutions compared with the proven correct serial methods, like the Hines method used in the NEURON simulation platform. Based on the theories in parallel computing , a parallel algorithm will yield an identical result as its corresponding serial algorithm, if and only if the data process order in the parallel algorithm is consistent with data dependency in the serial method. The Hines method has two symmetrical phases: triangularization and back-substitution. By analyzing the serial computing Hines method , we find that its data dependency can be formulated as a tree structure, where the nodes on the tree represent the compartments of the detailed neuron model. In the triangularization process, the value of each node depends on its children nodes. In contrast, during the back-substitution process, the value of each node is dependent on its parent node (Fig. ). Thus, we can compute nodes on different branches in parallel as their values are not dependent. 34 55 1d Based on the data dependency of the serial computing Hines method, we propose three conditions to make sure a parallel method will yield identical solutions as the serial computing Hines method: (1) The tree morphology and initial values of all nodes are identical to those in the serial computing Hines method; (2) In the triangularization phase, a node can be processed if and only if all its children nodes are already processed; (3) In the back-substitution phase, a node can be processed only if its parent node is already processed. Once a parallel computing method satisfies these three conditions, it will produce identical solutions as the serial computing method. Computational cost of cellular-level parallel computing method Aby teoretycznie ocenić czas pracy, czyli wydajność, metod obliczeniowych seryjnych i równoległych, wprowadzamy i sformułujemy pojęcie kosztów obliczeniowych w następujący sposób: and threads (basic computational units) to perform triangularization, parallel triangularization equals to divide the node set lub Wejście subsets, i.e., = { , , … } where the size of each subset | | ≤ , i.e., at most nodes can be processed each step since there are only threads. The process of the triangularization phase follows the order: → → … → , and nodes in the same subset Możemy to zrobić równolegle, więc zdefiniujemy | (the size of set , i.e., here) as the computational cost of the parallel computing method. In short, we define the computational cost of a parallel method as the number of steps it takes in the triangularization phase. Because the back-substitution is symmetrical with triangularization, the total cost of the entire solving equation phase is twice that of the triangularization phase. T k V T n V V1 V2 Vn Vi k k k V1 V2 Vn VI V V n Mathematical scheduling problem Based on the simulation accuracy and computational cost, we formulate the parallelization problem as a mathematical scheduling problem: Given a tree = { , Pozytywny integer , where is the node-set and is the edge set. Define partition ( ) = { , , … }, | | ≤ , 1 ≤ ≤ n, where | | indicates the cardinal number of subset , i.e., the number of nodes in , and for each node ∈ , all its children nodes { | ∈children( )} must in a previous subset , where 1 ≤ < Naszym celem jest znalezienie optymalnej partycji ( ) whose computational cost | ( )| is minimal. T V E k V E P V V1 V2 Vn Vi k i Vi Vi Vi v VI c c v Vj j i P* V P* V Here subset consists of all nodes that will be computed at -th step (Fig. ), so | | ≤ indicates that we can compute nodes each step at most because the number of available threads is . The restriction “for each node ∈ , all its children nodes { | ∈children( )} must in a previous subset , where 1 ≤ » ” indicates that node can be processed only if all its child nodes are processed. VI i 2e Vi k k k v Vi c c v Vj j i v DHS implementation We aim to find an optimal way to parallelize the computation of solving linear equations for each neuron model by solving the mathematical scheduling problem above. To get the optimal partition, DHS first analyzes the topology and calculates the depth ( ) for all nodes ∈ . Then, the following two steps will be executed iteratively until every node ∈ is assigned to a subset: (1) find all candidate nodes and put these nodes into candidate set . A node is a candidate only if all its child nodes have been processed or it does not have any child nodes. (2) if | ≤ ≤ ≤ , i.e., the number of candidate nodes is smaller or equivalent to the number of available threads, remove all nodes in and put them into , otherwise, remove deepest nodes from and add them to subset . Label these nodes as processed nodes (Fig. ). After filling in subset , go to step (1) to fill in the next subset . d v v V v V Q Q k Q V*i k Q Vi 2D Vi Vi+1 Correctness proof for DHS After applying DHS to a neural tree = { , }, we get a partition ( ) = { , , … }, | | ≤ , 1 ≤ ≤ . Nodes in the same subset Będą one obliczane równolegle, biorąc steps to perform triangularization and back-substitution, respectively. We then demonstrate that the reordering of the computation in DHS will result in a result identical to the serial Hines method. T V E P V V1 V2 Vn Vi k i n Vi n The partition ( ) obtained from DHS decides the computation order of all nodes in a neural tree. Below we demonstrate that the computation order determined by ( ) satisfies the correctness conditions. ( ) is obtained from the given neural tree . Operations in DHS do not modify the tree topology and values of tree nodes (corresponding values in the linear equations), so the tree morphology and initial values of all nodes are not changed, which satisfies condition 1: the tree morphology and initial values of all nodes are identical to those in serial Hines method. In triangularization, nodes are processed from subset to . As shown in the implementation of DHS, all nodes in subset are selected from the candidate set , and a node can be put into only if all its child nodes have been processed. Thus the child nodes of all nodes in are in { , , … }, meaning that a node is only computed after all its children have been processed, which satisfies condition 2: in triangularization, a node can be processed if and only if all its child nodes are already processed. In back-substitution, the computation order is the opposite of that in triangularization, i.e., from to . As shown before, the child nodes of all nodes in are in { , , … }, so parent nodes of nodes in are in { , , … }, which satisfies condition 3: in back-substitution, a node can be processed only if its parent node is already processed. P V P V P V T V1 Vn VI Q Q Vi w1 w2 Vi-1 Vn V1 Vi V1 V2 Vi-1 Vi I + 1 Vi+2 Vn Optimality proof for DHS The idea of the proof is that if there is another optimal solution, it can be transformed into our DHS solution without increasing the number of steps the algorithm requires, thus indicating that the DHS solution is optimal. For each subset w ( ), DHS moves (thread number) deepest nodes from the corresponding candidate set Dwóch . If the number of nodes in is smaller than , move all nodes from to . To simplify, we introduce , indicating the depth sum of Najgłębsze węzły w . All subsets in ( ) satisfy the max-depth criteria (Supplementary Fig. ): . We then prove that selecting the deepest nodes in each iteration makes an optimal partition. If there exists an optimal partition = { , , … } containing subsets that do not satisfy the max-depth criteria, we can modify the subsets in ( ) so that all subsets consist of the deepest nodes from and the number of subsets ( | ( )|) remain the same after modification. VI P V k Qi Vi Qi k Qi Vi Di k Qi P V 6a P(V) P*(V) V*1 V*2 V*s P* V Q P* V Without any loss of generalization, we start from the first subset not satisfying the criteria, i.e., . There are two possible cases that will make not satisfy the max-depth criteria: (1) | | < and there exist some valid nodes in that are not put to ; (2) | | = but nodes in are not the deepest nodes in . V*i V*i V * I k Qi V * I V*i k V * I k Qi For case (1), because some candidate nodes are not put to , węzły te muszą znajdować się w następnych podzbiorach. jako | , we can move the corresponding nodes from the subsequent subsets to , which will not increase the number of subsets and make satisfy the criteria (Supplementary Fig. , top). For case (2), | | = , these deeper nodes that are not moved from the candidate set into must be added to subsequent subsets (Supplementary Fig. , bottom). These deeper nodes can be moved from subsequent subsets to through the following method. Assume that after filling , is picked and one of the -th deepest nodes Jest nadal w , thus Zostaną one umieszczone w kolejnym podsumowaniu ( > ). We first move from to + , then modify subset + as follows: if | + | ≤ and none of the nodes in + is the parent of node , stop modifying the latter subsets. Otherwise, modify + as follows (Supplementary Fig. ): if the parent node of is in + , move this parent node to + ; else move the node with minimum depth from + to + Po dostosowaniu , modify subsequent subsets + , + więcej , … W ten sam sposób, wreszcie, poruszając się from to . V*i V * I < k V*i V*i 6b V*i k Qi V*i 6b V*i V*i v k v’ Qi V” V * J j i v V*i V*i 1 V*i 1 V*i 1 k V*i 1 v V*i 1 6c v V*i 1 V*i 2 V * I 1 V*i 2 V*i V*i 1 V*i 2 V*j-1 v’ V*j V * I Dzięki strategii modyfikacji opisanej powyżej możemy zastąpić wszystkie płaskie węzły w Z tą -th deepest node in and keep the number of subsets, i.e., | ( )| the same after modification. We can modify the nodes with the same strategy for all subsets in ( ) that do not contain the deepest nodes. Finally, all subsets ∈ ( ) can satisfy the max-depth criteria, and | ( )| does not change after modifying. V * I k Qi P* V P* V V*i P* V P* V In conclusion, DHS generates a partition ( ), and all subsets ∈ ( ) satisfy the max-depth condition: . For any other optimal partition ( ) we can modify its subsets to make its structure the same as ( ), i.e., each subset consists of the deepest nodes in the candidate set, and keep | ( ) the same after modification. So, the partition ( ) obtained from DHS is one of the optimal partitions. P V Vi P V P* V P V P* V | P V GPU implementation and memory boosting To achieve high memory throughput, GPU utilizes the memory hierarchy of (1) global memory, (2) cache, (3) register, where global memory has large capacity but low throughput, while registers have low capacity but high throughput. We aim to boost memory throughput by leveraging the memory hierarchy of GPU. GPU wykorzystuje architekturę SIMT (Single-Instruction, Multiple-Thread). Warps są podstawowymi jednostkami planowania na GPU (warp jest grupą 32 równoległych pasm). . Correctly ordering the nodes is essential for this batching of computation in warps, to make sure DHS obtains identical results as the serial Hines method. When implementing DHS on GPU, we first group all cells into multiple warps based on their morphologies. Cells with similar morphologies are grouped in the same warp. We then apply DHS on all neurons, assigning the compartments of each neuron to multiple threads. Because neurons are grouped into warps, the threads for the same neuron are in the same warp. Therefore, the intrinsic synchronization in warps keeps the computation order consistent with the data dependency of the serial Hines method. Finally, threads in each warp are aligned and rearranged according to the number of compartments. 46 Gdy warp ładuje wstępnie wyrównane i kolejno przechowywane dane z pamięci globalnej, może w pełni wykorzystać pamięć podręczną, co prowadzi do wysokiej przepustowości pamięci, podczas gdy dostęp do danych przechowywanych w rozproszeniu zmniejszyłby przepustowość pamięci. Po przydzieleniu oddziałów i ponownym uporządkowaniu przewodów, przenosimy dane w pamięci globalnej, aby uczynić je spójnymi z poleceniami obliczeniowymi, aby warpowie mogli ładować kolejno przechowywane dane podczas wykonywania programu. Full-spine and few-spine biophysical models We used the published human pyramidal neuron . The membrane capacitance m = 0.44 μF cm-2, membrane resistance m = 48,300 Ω cm2, and axial resistivity a = 261.97 Ω cm. In this model, all dendrites were modeled as passive cables while somas were active. The leak reversal potential l = -83,1 mV. Kanały jonowe takie jak Na+ i K+ zostały włożone na sumę i początkowy akson, a ich potencjał odwrotny był Na = 67.6 mV, K = -102 mV respectively. All these specific parameters were set the same as in the model of Eyal, et al. , w celu uzyskania dalszych informacji prosimy zapoznać się z opublikowanym modelem (ModelDB, dostęp nr 238347). 51 c r r E E E 51 In the few-spine model, the membrane capacitance and maximum leak conductance of the dendritic cables 60 μm away from soma were multiplied by a spine factor to approximate dendritic spines. In this model, spine was set to 1.9. Only the spines that receive synaptic inputs were explicitly attached to dendrites. F F W modelu pełnego kręgosłupa wszystkie kręgosłupy były wyraźnie przywiązane do dendrytów. Obliczyliśmy gęstość kręgosłupa z przebudowanym neuronem w Eyal et al. . The spine density was set to 1.3 μm-1, and each cell contained 24994 spines on dendrites 60 μm away from the soma. 51 The morphologies and biophysical mechanisms of spines were the same in few-spine and full-spine models. The length of the spine neck neck = 1.35 μm and the diameter neck = 0.25 μm, whereas the length and diameter of the spine head were 0.944 μm, i.e., the spine head area was set to 2.8 μm2. Both spine neck and spine head were modeled as passive cables, with the reversal potential = -86 mV. Specyficzna zdolność membranowa, odporność membranowa i oporność axialna były takie same jak w przypadku dendrytów. L D El Synaptic inputs Badaliśmy pobudliwość neuronalną zarówno dla rozproszonych, jak i grupowych wejść synaptycznych. Wszystkie aktywowane synapsy były przymocowane do terminala głowy kręgosłupa. W przypadku rozproszonych wejść wszystkie aktywowane synapsy były losowo rozprowadzane na wszystkich dendrytach. W przypadku wejść klasterowych każdy zbiornik składał się z 20 aktywowanych synaps, które były równomiernie rozprowadzane na pojedynczym losowo wybranym oddziale. AMPA-based and NMDA-based synaptic currents were simulated as in Eyal et al.’s work. AMPA conductance was modeled as a double-exponential function and NMDA conduction as a voltage-dependent double-exponential function. For the AMPA model, the specific rise and decay were set to 0.3 and 1.8 ms. For the NMDA model, rise and decay were set to 8.019 and 34.9884 ms, respectively. The maximum conductance of AMPA and NMDA were 0.73 nS and 1.31 nS. τ τ τ τ Background noise We attached background noise to each cell to simulate a more realistic environment. Noise patterns were implemented as Poisson spike trains with a constant rate of 1.0 Hz. Each pattern started at start = 10 ms and lasted until the end of the simulation. We generated 400 noise spike trains for each cell and attached them to randomly-selected synapses. The model and specific parameters of synaptic currents were the same as described in , except that the maximum conductance of NMDA was uniformly distributed from 1.57 to 3.275, resulting in a higher AMPA to NMDA ratio. t Synaptic Inputs Exploring neuronal excitability We investigated the spike probability when multiple synapses were activated simultaneously. For distributed inputs, we tested 14 cases, from 0 to 240 activated synapses. For clustered inputs, we tested 9 cases in total, activating from 0 to 12 clusters respectively. Each cluster consisted of 20 synapses. For each case in both distributed and clustered inputs, we calculated the spike probability with 50 random samples. Spike probability was defined as the ratio of the number of neurons fired to the total number of samples. All 1150 samples were simulated simultaneously on our DeepDendrite platform, reducing the simulation time from days to minutes. Wykonywanie zadań AI przy użyciu platformy DeepDendrite Conventional detailed neuron simulators lack two functionalities important to modern AI tasks: (1) alternately performing simulations and weight updates without heavy reinitialization and (2) simultaneously processing multiple stimuli samples in a batch-like manner. Here we present the DeepDendrite platform, which supports both biophysical simulating and performing deep learning tasks with detailed dendritic models. DeepDendrite consists of three modules (Supplementary Fig. ): (1) an I/O module; (2) a DHS-based simulating module; (3) a learning module. When training a biophysically detailed model to perform learning tasks, users first define the learning rule, then feed all training samples to the detailed model for learning. In each step during training, the I/O module picks a specific stimulus and its corresponding teacher signal (if necessary) from all training samples and attaches the stimulus to the network model. Then, the DHS-based simulating module initializes the model and starts the simulation. After simulation, the learning module updates all synaptic weights according to the difference between model responses and teacher signals. After training, the learned model can achieve performance comparable to ANN. The testing phase is similar to training, except that all synaptic weights are fixed. 5 HPC-Net model Image classification is a typical task in the field of AI. In this task, a model should learn to recognize the content in a given image and output the corresponding label. Here we present the HPC-Net, a network consisting of detailed human pyramidal neuron models that can learn to perform image classification tasks by utilizing the DeepDendrite platform. HPC-Net has three layers, i.e., an input layer, a hidden layer, and an output layer. The neurons in the input layer receive spike trains converted from images as their input. Hidden layer neurons receive the output of input layer neurons and deliver responses to neurons in the output layer. The responses of the output layer neurons are taken as the final output of HPC-Net. Neurons between adjacent layers are fully connected. For each image stimulus, we first convert each normalized pixel to a homogeneous spike train. For pixel with coordinates ( ) in the image, the corresponding spike train has a constant interspike interval ISI( ) (in ms) which is determined by the pixel value ( ) as shown in Eq. ( ). x, y τ x, y p x, y 1 In our experiment, the simulation for each stimulus lasted 50 ms. All spike trains started at 9 + ISI ms and lasted until the end of the simulation. Then we attached all spike trains to the input layer neurons in a one-to-one manner. The synaptic current triggered by the spike arriving at time is given by τ t0 where is the post-synaptic voltage, the reversal potential syn = 1 mV, the maximum synaptic conductance max = 0.05 μS, and the time constant = 0.5 ms. v E g τ Neurons in the input layer were modeled with a passive single-compartment model. The specific parameters were set as follows: membrane capacitance m = 1,0 μF cm-2, opór membranowy m = 104 Ω cm2, axial resistivity a = 100 Ω cm, reversal potential of passive compartment l = 0 mV. c r r E The hidden layer contains a group of human pyramidal neuron models, receiving the somatic voltages of input layer neurons. The morphology was from Eyal, et al. , and all neurons were modeled with passive cables. The specific membrane capacitance m = 1,5 μF cm-2, opór membranowy m = 48,300 Ω cm2, axial resistivity a = 261.97 Ω cm, and the reversal potential of all passive cables l = 0 mV. Input neurons could make multiple connections to randomly-selected locations on the dendrites of hidden neurons. The synaptic current activated by the -th synapse of the -th input neuron on neuron ’s dendrite is defined as in Eq. ( ), where is the synaptic conductance, is the synaptic weight, is the ReLU-like somatic activation function, and is the somatic voltage of the -th input neuron at time . 51 c r r E k i j 4 gijk Wijk i t Neurons in the output layer were also modeled with a passive single-compartment model, and each hidden neuron only made one synaptic connection to each output neuron. All specific parameters were set the same as those of the input neurons. Synaptic currents activated by hidden neurons are also in the form of Eq. ( ). 4 Image classification with HPC-Net For each input image stimulus, we first normalized all pixel values to 0.0-1.0. Then we converted normalized pixels to spike trains and attached them to input neurons. Somatic voltages of the output neurons are used to compute the predicted probability of each class, as shown in equation , where is the probability of -th class predicted by the HPC-Net, is the average somatic voltage from 20 ms to 50 ms of the -th output neuron, and indicates the number of classes, which equals the number of output neurons. The class with the maximum predicted probability is the final classification result. In this paper, we built the HPC-Net with 784 input neurons, 64 hidden neurons, and 10 output neurons. 6 pi i i C Synaptic plasticity rules for HPC-Net Inspired by previous work , we use a gradient-based learning rule to train our HPC-Net to perform the image classification task. The loss function we use here is cross-entropy, given in Eq. ( ), where is the predicted probability for class , indicates the actual class the stimulus image belongs to, = 1 if input image belongs to class , and = 0 if not. 36 7 pi i Yi yi i yi When training HPC-Net, we compute the update for weight (the synaptic weight of the -th synapse connecting neuron to neuron ) at each time step. After the simulation of each image stimulus, is updated as shown in Eq. ( ): Wijk k i j Wijk 8 Here is the learning rate, is the update value at time , , are somatic voltages of neuron and respectively, is the -th synaptic current activated by neuron on neuron , its synaptic conductance, is the transfer resistance between the -th connected compartment of neuron on neuron ’s dendrite to neuron ’s soma, s = 30 ms, e = 50 ms are start time and end time for learning respectively. For output neurons, the error term can be computed as shown in Eq. ( W przypadku ukrytych neuronów termin błędu jest obliczany z terminów błędu w warstwie wyjściowej, podanych w Eq. ( ). t vj vi i j Iczak k i j gijk rijk k i j j t t 10 11 Since all output neurons are single-compartment, equals to the input resistance of the corresponding compartment, . Transfer and input resistances are computed by NEURON. Mini-batch training is a typical method in deep learning for achieving higher prediction accuracy and accelerating convergence. DeepDendrite also supports mini-batch training. When training HPC-Net with mini-batch size Batch, my robimy batch copies of HPC-Net. During training, each copy is fed with a different training sample from the batch. DeepDendrite first computes the weight update for each copy separately. After all copies in the current training batch are done, the average weight update is calculated and weights in all copies are updated by this same amount. N N Odporność na ataki przeciwnika dzięki HPC-Net Aby wykazać solidność HPC-Net, przetestowaliśmy dokładność przewidywania na próbkach przeciwnika i porównaliśmy ją z analogowym ANN (jednym z tą samą strukturą 784-64-10 i aktywacją ReLU, dla uczciwego porównania w naszym HPC-Net każdy neuron wejściowy wykonał tylko jedno połączenie synaptyczne z każdym ukrytym neuronem). Najpierw przeszkoliliśmy HPC-Net i ANN z oryginalnym zestawem szkoleniowym (oryginalne czyste obrazy). Następnie dodaliśmy hałas przeciwnika do zestawu testowego i zmierzyliśmy ich dokładność przewidywania na zestawie testowym. , generowanie hałasu przeciwnika za pomocą metody FGSM . ANN was trained with PyTorch , and HPC-Net was trained with our DeepDendrite. For fairness, we generated adversarial noise on a significantly different network model, a 20-layer ResNet . The noise level ranged from 0.02 to 0.2. We experimented on two typical datasets, MNIST i Fashion-MNIST . Results show that the prediction accuracy of HPC-Net is 19% and 16.72% higher than that of the analogous ANN, respectively. 98 99 93 100 101 95 96 Raport podsumowujący Więcej informacji na temat projektu jest dostępnych w linked to this article. Nature Portfolio Reporting Summary Data availability Dane, które wspierają wyniki tego badania są dostępne w papierze, dodatkowych informacjach i plikach danych źródłowych dostarczonych wraz z tym dokumentem. – Są dostępne w Zbiór danych MNIST jest publicznie dostępny na Zbiór danych Fashion-MNIST jest publicznie dostępny pod adresem ... Dostarczane są w tym dokumencie. 3 6 https://github.com/pkuzyc/DeepDendrite http://yann.lecun.com/exdb/mnist https://github.com/zalandoresearch/fashion-mnist Source data Code availability The source code of DeepDendrite as well as the models and code used to reproduce Figs. – in this study are available at . 3 6 https://github.com/pkuzyc/DeepDendrite References McCulloch, W. S. & Pitts, W. A logical calculus of the ideas immanent in nervous activity. , 115–133 (1943). Bull. Math. Biophys. 5 LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. , 436–444 (2015). Nature 521 Poirazi, P., Brannon, T. & Mel, B. W. Arytmetyka sumowania synaptycznego podpięciu w komórce piramidalnej modelu CA1. London, M. & Häusser, M. Dendritic computation. , 503–532 (2005). Annu. Rev. Neurosci. 28 Branco, T. & Häusser, M. The single dendritic branch as a fundamental functional unit in the nervous system. , 494–502 (2010). Curr. Opin. Neurobiol. 20 Stuart, G. J. & Spruston, N. Integracja dendrytowa: 60 lat postępu. Nat. Neurosci. 18, 1713–1721 (2015). Poirazi, P. & Papoutsi, A. Illuminating dendritic function with computational models. , 303–321 (2020). Nat. Rev. Neurosci. 21 Yuste, R. & Denk, W. Kręgosłupy dendrytyczne jako podstawowe jednostki funkcjonalne integracji neuronowej. Engert, F. & Bonhoeffer, T. Dendritic spine changes associated with hippocampal long-term synaptic plasticity. , 66–70 (1999). Nature 399 Yuste, R. Dendritic spines and distributed circuits. , 772–781 (2011). Neuron 71 Yuste, R. Electrical compartmentalization in dendritic spines. , 429–449 (2013). Annu. Rev. Neurosci. 36 Rall, W. Rozgałęzienia drzew dendrytowych i odporność błony motoneuronowej. Eksp. Neurol. 1, 491–527 (1959). Segev, I. & Rall, W. Computational study of an excitable dendritic spine. , 499–523 (1988). J. Neurophysiol. 60 Silver, D. et al. Mastering the game of go with deep neural networks and tree search. , 484–489 (2016). Nature 529 Silver, D. et al. A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. , 1140–1144 (2018). Science 362 McCloskey, M. & Cohen, N. J. Catastrophic interference in connectionist networks: the sequential learning problem. , 109–165 (1989). Psychol. Learn. Motiv. 24 French, R. M. Catastrophic forgetting in connectionist networks. , 128–135 (1999). Trends Cogn. Sci. 3 Naud, R. & Sprekeler, H. Sparse bursts optimize information transmission in a multiplexed neural code. , E6329–E6338 (2018). Proc. Natl Acad. Sci. USA 115 Sacramento, J., Costa, R. P., Bengio, Y. & Senn, W. Dendritic cortical microcircuits approximate the backpropagation algorithm. in (NeurIPS*,* 2018). Advances in Neural Information Processing Systems 31 (NeurIPS 2018) Payeur, A., Guerguiev, J., Zenke, F., Richards, B. A. & Naud, R. Burst-dependent synaptic plasticity can coordinate learning in hierarchical circuits. , 1010–1019 (2021). Nat. Neurosci. 24 Bicknell, B. A. & Häusser, M. Reguła uczenia się synaptycznego w celu wykorzystania obliczeń dendrytowych nieliniowych Neuron 109, 4001–4017 (2021). Moldwin, T., Kalmenson, M. & Segev, I. The gradient clusteron: a model neuron that learns to solve classification tasks via dendritic nonlinearities, structural plasticity, and gradient descent. , e1009015 (2021). PLoS Comput. Biol. 17 Hodgkin, A. L. & Huxley, A. F. A quantitative description of membrane current and Its application to conduction and excitation in nerve. , 500–544 (1952). J. Physiol. 117 Rall, W. Theory of physiological properties of dendrites. , 1071–1092 (1962). Ann. N. Y. Acad. Sci. 96 Hines, M. L. & Carnevale, N. T. The NEURON simulation environment. , 1179–1209 (1997). Neural Comput. 9 Bower, J. M. & Beeman, D. in (eds Bower, J.M. & Beeman, D.) 17–27 (Springer New York, 1998). The Book of GENESIS: Exploring Realistic Neural Models with the GEneral NEural SImulation System Hines, M. L., Eichner, H. & Schürmann, F. Neuron splitting in compute-bound parallel network simulations enables runtime scaling with twice as many processors. , 203–210 (2008). J. Comput. Neurosci. 25 Hines, M. L., Markram, H. & Schürmann, F. Fully implicit parallel simulation of single neurons. , 439–448 (2008). J. Comput. Neurosci. 25 Ben-Shalom, R., Liberman, G. i Korngreen, A. Przyspieszanie modelowania oddziałowego na jednostce graficznej. Tsuyuki, T., Yamamoto, Y. & Yamazaki, T. Efficient numerical simulation of neuron models with spatial structure on graphics processing units. In (eds Hirose894Akiraet al.) 279–285 (Springer International Publishing, 2016). Proc. 2016 International Conference on Neural Information Processing Vooturi, D. T., Kothapalli, K. & Bhalla, U. S. Parallelizing Hines Matrix Solver in Neuron Simulations on GPU. In 388–397 (IEEE, 2017). Proc. IEEE 24th International Conference on High Performance Computing (HiPC) Huber, F. Efektywny rozwiązywacz drzew dla matryc hin na GPU. Preprint na https://arxiv.org/abs/1810.12742 (2018). Korte, B. & Vygen, J. 6 edn (Springer, 2018). Combinatorial Optimization Theory and Algorithms Gebali, F. Algorytmy i obliczenia równoległe (Wiley, 2011) Kumbhar, P. et al. CoreNEURON: Zoptymalizowany silnik obliczeniowy dla symulatora NEURON. Front. Neuroinform. 13, 63 (2019). Urbanczik, R. & Senn, W. Learning by the dendritic prediction of somatic spiking. , 521–528 (2014). Neuron 81 Ben-Shalom, R., Aviv, A., Razon, B. & Korngreen, A. Optimizing ion channel models using a parallel genetic algorithm on graphical processors. , 183–194 (2012). J. Neurosci. Methods 206 Mascagni, M. Algorytm równoległy dla rozwiązań obliczeniowych do arbitralnie rozgałęzionych modeli neuronów kablowych. McDougal, R. A. et al. Twenty years of modelDB and beyond: building essential modeling tools for the future of neuroscience. , 1–10 (2017). J. Comput. Neurosci. 42 Migliore, M., Messineo, L. & Ferrante, M. Dendritic Ih selectively blocks temporal summation of unsynchronized distal inputs in CA1 pyramidal neurons. , 5–13 (2004). J. Comput. Neurosci. 16 Hemond, P. et al. Różne klasy komórek piramidalnych wykazują wzajemnie wykluczające się wzorce strzelania w strefie hipokampalnej CA3b. Hay, E., Hill, S., Schürmann, F., Markram, H. & Segev, I. Models of neocortical layer 5b pyramidal cells capturing a wide range of dendritic and perisomatic active Properties. , e1002107 (2011). PLoS Comput. Biol. 7 Masoli, S., Solinas, S. & D’Angelo, E. Action potential processing in a detailed purkinje cell model reveals a critical role for axonal compartmentalization. , 47 (2015). Front. Cell. Neurosci. 9 Lindroos, R. et al. Basal ganglia neuromodulation over multiple temporal and structural scales—simulations of direct pathway MSNs investigate the fast onset of dopaminergic effects and predict the role of Kv4.2. , 3 (2018). Front. Neural Circuits 12 Migliore, M. et al. Gromady synaptyczne działają jako operatorzy zapachu w żarówce zapachowej. Proc. Natl Acad. Sci. USa 112, 8499–8504 (2015). NVIDIA. . (2021). CUDA C++ Programming Guide https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html NVIDIA. . (2021). CUDA C++ Best Practices Guide https://docs.nvidia.com/cuda/cuda-c-best-practices-guide/index.html Harnett, M. T., Makara, J. K., Spruston, N., Kath, W. L. & Magee, J. C. Synaptic amplification by dendritic spines enhances input cooperativity. , 599–602 (2012). Nature 491 Chiu, C. Q. et al. Compartmentalization of GABAergic inhibition by dendritic spines. , 759–762 (2013). Science 340 Tønnesen, J., Katona, G., Rózsa, B. & Nägerl, U. V. Spine neck plasticity regulates compartmentalization of synapses. , 678–685 (2014). Nat. Neurosci. 17 Eyal, G. et al. Human cortical pyramidal neurons: from spines to spikes via models. , 181 (2018). Front. Cell. Neurosci. 12 Koch, C. & Zador, A. The function of dendritic spines: devices subserving biochemical rather than electrical compartmentalization. , 413–422 (1993). J. Neurosci. 13 Koch, C. Dendritic spines. In (Oxford University Press, 1999). Biophysics of Computation Rapp, M., Yarom, Y. & Segev, I. The impact of parallel fiber background activity on the cable properties of cerebellar purkinje cells. , 518–533 (1992). Neural Comput. 4 Hines, M. Efficient computation of branched nerve equations. , 69–76 (1984). Int. J. Bio-Med. Comput. 15 Nayebi, A. & Ganguli, S. Biologically inspired protection of deep networks from adversarial attacks. Preprint at (2017). https://arxiv.org/abs/1703.09202 Goddard, N. H. & Hood, G. Large-Scale Simulation Using Parallel GENESIS. In (eds Bower James M. & Beeman David) 349-379 (Springer New York, 1998). The Book of GENESIS: Exploring Realistic Neural Models with the GEneral NEural SImulation System Migliore, M., Cannia, C., Lytton, W. W., Markram, H. & Hines, M. L. Parallel network simulations with NEURON. , 119 (2006). J. Comput. Neurosci. 21 Lytton, W. W. et al. Simulation neurotechnologies for advancing brain research: parallelizing large networks in NEURON. , 2063–2090 (2016). Neural Comput. 28 Valero-Lara, P. et al. cuHinesBatch: Solving multiple Hines systems on GPUs human brain project. In 566–575 (IEEE, 2017). Proc. 2017 International Conference on Computational Science Akar, N. A. et al. Arbor—A morphologically-detailed neural network simulation library for contemporary high-performance computing architectures. In 274–282 (IEEE, 2019). Proc. 27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP) Ben-Shalom, R. et al. NeuroGPU: Accelerating multi-compartment, biophysically detailed neuron simulations on GPUs. , 109400 (2022). J. Neurosci. Methods 366 Rempe, M. J. & Chopp, D. L. A predictor-corrector algorithm for reaction-diffusion equations associated with neural activity on branched structures. , 2139–2161 (2006). SIAM J. Sci. Comput. 28 Kozloski, J. & Wagner, J. Ultraskalowalne rozwiązanie do symulacji tkanki nerwowej na dużą skalę. Front. Neuroinform. 5, 15 (2011). Jayant, K. et al. Ukierunkowane rejestry napięcia wewnątrzkomórkowego z pędów dendrytowych przy użyciu nanopipetów powlekanych kropkami kwantowymi. Nat. Nanotechnol. 12, 335–342 (2017). Palmer, L. M. & Stuart, G. J. Membrane potential changes in dendritic spines during action potentials and synaptic input. , 6897–6903 (2009). J. Neurosci. 29 Nishiyama, J. & Yasuda, R. Biochemical computation for spine structural plasticity. , 63–75 (2015). Neuron 87 Yuste, R. & Bonhoeffer, T. Morphological changes in dendritic spines associated with long-term synaptic plasticity. , 1071–1089 (2001). Annu. Rev. Neurosci. 24 Holtmaat, A. & Svoboda, K. Experience-dependent structural synaptic plasticity in the mammalian brain. , 647–658 (2009). Nat. Rev. Neurosci. 10 Caroni, P., Donato, F. & Muller, D. Structural plasticity upon learning: regulation and functions. , 478–490 (2012). Nat. Rev. Neurosci. 13 Keck, T. et al. Masywna restrukturyzacja obwodów neuronowych podczas reorganizacji funkcjonalnej dorosłej kory wzrokowej. Nat. Neurosci. 11, 1162 (2008). Hofer, S. B., Mrsic-Flogel, T. D., Bonhoeffer, T. & Hübener, M. Experience leaves a lasting structural trace in cortical circuits. , 313–317 (2009). Nature 457 Trachtenberg, J. T. et al. Long-term in vivo imaging of experience-dependent synaptic plasticity in adult cortex. , 788–794 (2002). Nature 420 Marik, S. A., Yamahachi, H., McManus, J. N., Szabo, G. & Gilbert, C. D. Axonal dynamics of excitatory and inhibitory neurons in somatosensory cortex. , e1000395 (2010). PLoS Biol. 8 Xu, T. et al. Rapid formation and selective stabilization of synapses for enduring motor memories. , 915–919 (2009). Nature 462 Albarran, E., Raissi, A., Jáidar, O., Shatz, C. J. & Ding, J. B. Enhancing motor learning by increasing the stability of newly formed dendritic spines in the motor cortex. , 3298–3311 (2021). Neuron 109 Branco, T. & Häusser, M. Synaptic integration gradients in single cortical pyramidal cell dendrites. , 885–892 (2011). Neuron 69 Major, G., Larkum, M. E. & Schiller, J. Active properties of neocortical pyramidal neuron dendrites. , 1–24 (2013). Annu. Rev. Neurosci. 36 Gidon, A. et al. Dendritic action potentials and computation in human layer 2/3 cortical neurons. , 83–87 (2020). Science 367 Doron, M., Chindemi, G., Muller, E., Markram, H. & Segev, I. Timed synaptic inhibition shapes NMDA spikes, influencing local dendritic processing and global I/O properties of cortical neurons. , 1550–1561 (2017). Cell Rep. 21 Du, K. et al. Cell-type-specific inhibition of the dendritic plateau potential in striatal spiny projection neurons. , E7612–E7621 (2017). Proc. Natl Acad. Sci. USA 114 Smith, S. L., Smith, I. T., Branco, T. & Häusser, M. Dendritic spikes enhance stimulus selectivity in cortical neurons in vivo. , 115–120 (2013). Nature 503 Xu, N.-l et al. Nonlinear dendritic integration of sensory and motor input during an active sensing task. , 247–251 (2012). Nature 492 Takahashi, N., Oertner, T. G., Hegemann, P. & Larkum, M. E. Active cortical dendrites modulate perception. , 1587–1590 (2016). Science 354 Sheffield, M. E. & Dombeck, D. A. Calcium transient prevalence across the dendritic arbour predicts place field properties. , 200–204 (2015). Nature 517 Markram, H. et al. Reconstruction and simulation of neocortical microcircuitry. , 456–492 (2015). Cell 163 Billeh, Y. N. et al. Systematic integration of structural and functional data into multi-scale models of mouse primary visual cortex. , 388–403 (2020). Neuron 106 Hjorth, J. et al. The microcircuits of striatum in silico. , 202000671 (2020). Proc. Natl Acad. Sci. USA 117 Guerguiev, J., Lillicrap, T. P. & Richards, B. A. Towards deep learning with segregated dendrites. , e22901 (2017). elife 6 Iyer, A. et al. Zapobieganie katastrofom: aktywne dendryty umożliwiają uczenie się wielozadaniowe w dynamicznych środowiskach. Front. Neurorobot. 16, 846219 (2022). Jones, I. S. & Kording, K. P. Might a single neuron solve interesting machine learning problems through successive computations on its dendritic tree? , 1554–1571 (2021). Neural Comput. 33 Bird, A. D., Jedlicka, P. & Cuntz, H. Dendritic normalisation improves learning in sparsely connected artificial neural networks. , e1009202 (2021). PLoS Comput. Biol. 17 Goodfellow, I. J., Shlens, J. & Szegedy, C. Explaining and harnessing adversarial examples. In (ICLR, 2015). 3rd International Conference on Learning Representations (ICLR) Papernot, N., McDaniel, P. & Goodfellow, I. Transferability in machine learning: from phenomena to black-box attacks using adversarial samples. Preprint at (2016). https://arxiv.org/abs/1605.07277 Lecun, Y., Bottou, L., Bengio, Y. & Haffner, P. Gradient-based learning applied to document recognition. , 2278–2324 (1998). Proc. IEEE 86 Xiao, H., Rasul, K. & Vollgraf, R. Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. Preprint at (2017). http://arxiv.org/abs/1708.07747 Bartunov, S. et al. Assessing the scalability of biologically-motivated deep learning algorithms and architectures. In (NeurIPS, 2018). Advances in Neural Information Processing Systems 31 (NeurIPS 2018) Rauber, J., Brendel, W. & Bethge, M. Foolbox: A Python toolbox to benchmark the robustness of machine learning models. In (2017). Reliable Machine Learning in the Wild Workshop, 34th International Conference on Machine Learning Rauber, J., Zimmermann, R., Bethge, M. & Brendel, W. Foolbox native: fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX. , 2607 (2020). J. Open Source Softw. 5 Paszke, A. et al. PyTorch: An imperative style, high-performance deep learning library. In (NeurIPS, 2019). Advances in Neural Information Processing Systems 32 (NeurIPS 2019) He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In 770–778 (IEEE, 2016). Proc. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Acknowledgements The authors sincerely thank Dr. Rita Zhang, Daochen Shi and members at NVIDIA for the valuable technical support of GPU computing. This work was supported by the National Key R&D Program of China (No. 2020AAA0130400) to K.D. and T.H., National Natural Science Foundation of China (No. 61088102) to T.H., National Key R&D Program of China (No. 2022ZD01163005) to L.M., Key Area R&D Program of Guangdong Province (No. 2018B030338001) to T.H., National Natural Science Foundation of China (No. 61825101) to Y.T., Swedish Research Council (VR-M-2020-01652), Swedish e-Science Research Centre (SeRC), EU/Horizon 2020 No. 945539 (HBP SGA3), and KTH Digital Futures to J.H.K., J.H., and A.K., Swedish Research Council (VR-M-2021-01995) and EU/Horizon 2020 no. 945539 (HBP SGA3) to S.G. and A.K. Part of the simulations were enabled by resources provided by the Swedish National Infrastructure for Computing (SNIC) at PDC KTH partially funded by the Swedish Research Council through grant agreement no. 2018-05973. Niniejszy artykuł jest dostępny w naturze na podstawie licencji CC by 4.0 Deed (Attribution 4.0 International). Ten dokument jest under CC by 4.0 Deed (Attribution 4.0 International) license. available on nature
