What is a Feed forward Neural Network (FNN)?
A Feedforward Neural Network is an artificial neural network wherein connections between the nodes do not form a cycle. The feedforward neural network was the first and simplest type of artificial neural network devised. In this network, the information moves in only one direction, forward, from the input nodes, through the hidden nodes (if any) and to the output nodes. There are no cycles or loops in the network.
In this repository, we will create a simple Feed forward Neural Network for binary classification of non-linearly seperable arbitary datset. This model will be compared to Sigmoid Neuron model on the same datset.
The Neural Network will be of the type as shown in image:
After succesfully realising the Feed Forward Network given in the figure, a more generic Neural Network will be worked upon for binary classification.
Afterwards, we will model a more generic class of FNN with multi-class classification and will play around a little bit.
The diagram for the FNN model with multi-class classification is given below-
