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
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)





Comments
Post a Comment