How To Craft A Deep Learning Model in Java (Without Sorcery, aka Frameworks)

Written by cleuton-sampaio | Published 2020/01/13
Tech Story Tags: java-top-story | deep-learning-top-story | how-to-create-ml-perceptron | deep-learning-training-modules | backpropagation | partial-derivatives-in-ml | machine-learning-top-story | hackernoon-top-story

TLDR An example of an MLP (Multilayer Perceptron), capable of classify iris flowers, using the four features described in the IRIS Dataset. The model is created just before we call fit() and I was inspired by the Keras model to create this API. The training consists of repeating the network calculation several times (epochs), taking each record and getting an output. We correct each weight according to its "responsibility" in the final error. More responsible weights receive greater correction. Backpropagation is to calculate the error and adjust the node (and bias) weights.via the TL;DR App
no story
Written by cleuton-sampaio | Founder: "pythondrops.com". Full-stack dev/ AI Engineer/ Professional Writer/ M.Sc. Rio de Janeiro
Published by HackerNoon on 2020/01/13
ABOUTHow hackers start their afternoons. We publish tech stories and build publishing software.

READEntirely free library read by hundreds of millions to learn anything about any technology.

WRITEHackerNoon elevates quality technology writing far and wide across the interwebs.

PARTNERHackerNoon works directly with tech companies to place ads by content relevancy