Skip to content

lightknight64bit/Neural-network-from-scratch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Neural-network-from-scratch

In the NNfromScratch.ipynb jupyter notebook, I aim to train an AND gate from scratch with Dense Neural networks. The graphical representation of the neural network used is given below:-

Neural network image

In the NNfromScratchWithOOPS.ipynb notebook, I train the MNIST Dataset with Dense Neural Networks coded fully from scratched. The neural network constructed has 1 input layer with 784 neurons, 1 hidden layer with 128 neurons and relu activation and 1 output layer with 10 neurons and softmax activation. The error metric used is MSE. The final MSE score comes out to be approximately 0.1.

Detailed explanation given in Notebooks