Skip to content

Latest commit

 

History

History
8 lines (7 loc) · 458 Bytes

README.md

File metadata and controls

8 lines (7 loc) · 458 Bytes

Neural Network

Neural Network with backpropagation. Implement a feed-forward neural network for classifying handwritten digits. Back propagation to compute the parameter derivatives for SGD and also do L2 regularization for SGD. tinyTOY.pkl.gz, MNIST(tinyMNIST.pkl.gz).

Convolution Nueral Networks

Conv2D layer in Keras to build a Convolutional Neural Network for the MNIST dataset. reshape the vector of each image into matrix for the use of Conv2D.