Neural Network

 Neural Network


What is a Neural Network

Deep Learning  is based on the function of a human brain, lets understand how does a Biological Neural Network look like


  • First step in the process is to calculate the weighted sum of the inputs
  • Second step in the process is to pass the calculated weighted  sum as input activation function to generate the output.


Activation Function

An Activation function takes the "weighted sum of input plus the bias" as the input to the function and decides whether it should be fired or not.

Types of Activation Functions

  • Sigmoid Function
  • Threshold Function
  • ReLU Function (Most Popular one in current Industry)
  • Hyperbolic Target Function

Sigmoid Function

Used for models where we have to predict the probability as an output. It exists between 0 and 1

Threshold Function

It is a thershold based activation function. If Y value is greater than a certain Value,
the function is activated and fired else not.It is a kind of stack Function.

ReLU Function

It is most widely used Activation Function and gives an output of X if  X is positive and 0 otherwise.

Hyperbolic Target Function

The function is similar to sigmoid function and is bound to range(-1,1)


Working of Neural Network




Comments

Popular posts from this blog

Overflow Error Computing

Deep Learning with python