Artificial Neural Network : Beginning of the AI revolution by@technoreview

Artificial Neural Network : Beginning of the AI revolution

June 23rd 2022 3,515 reads
Read on Terminal Reader
react to story with heart
react to story with light
react to story with boat
react to story with money
TechnoReview HackerNoon profile picture


According to Wikipedia : An artificial neural network is an interconnected group of nodes, akin to the vast network of neurons in a brain.
What comes to our mind when we hear the term Neural Network, which is quite obviously trending these days . Whenever we hear Neural Network, a slight glimpse of the pic given below comes to our mind
The first picture shows the biological neuron. It is the basic constituent of our nervous system. The basic functions of our body are performed through neural networks. The head neuron receives the signal from our brain and depending on the intensity of the signal, it passes through different neurons connected to the head neuron and performs the right task.
Therefore, an artificial neural network basically a model imagined or we can say inspired from the human brain. Let me clarify that the neural networks in our brain are not as simple and much complex than the artificial neural network we just saw. Although we can construct a complex neural network but the neural architecture of our brain is much more complex and yet unexplored.
Mathematically speaking, Artificial Neural Networks are highly complex composite functions providing the ability of computing non-linear problems to the computers.
The neural network consists of the layer of input signals or neurons where the information enters the neural network, a layer of output signal neurons where we can get the result out of the Network, and a number of various hidden layers in between.
A single Neuron
  1. x1, x2,…, xN: Inputs to the neuron. These can either be the actual observations from input layer or an intermediate value from one of the hidden layers.
  2. x0: Bias unit. This is a constant value added to the input of the activation function. It works similar to an intercept term and typically has +1 value.
  3. w0,w1, w2,…,wN: Weights on each input. Note that even bias unit has a weight.
  4. a: Output of the neuron which is calculated as:
f is the activation function
Neural Network lies in the heart of products such as self driving cars, image recognition software, recommender systems, AI drone surveillance, OCR(optical character recognition), spectrogramic representation of sound, text and speech analytics….etc.

Types of ANNs

There are currently 6 types of Neural Network mostly used in Neural Network Architecture in Deep Learning
  1. Feedforward Neural Network
  2. Recurrent Neural Network which is basically used in Long Short Term Memory (LSTM) projects
  3. Convolutional Neural Network
  4. Radial basis function Neural Network
  5. Kohonen Self Organizing Neural Network
  6. Modular Neural Network
On the basis of Hidden layers, we can classify them as
  1. 2-layer Neural Network(1 hidden layer)
  2. 3-layer Neural Network(2 hidden layer)
  3. Complex Neural Network
So, bigger the Neural Network, better it is.
Follow NITW Technoreview for more updates
react to story with heart
react to story with light
react to story with boat
react to story with money
. . . comments & more!