All the code files related to the deep learning course from PadhAI

MNIST classification using Multi-Layer Perceptron (MLP) with 2 hidden layers. Some weight-initializers and batch-normalization are implemented.

a simple neural network

Compare vanishing gradient problem case by case.

Fully connected neural network for digit classification using MNIST data

Generic L-layer 'straight in Python' fully connected Neural Network implementation using numpy.

The aim of this project is to implement an image classifier based on convolu- tional neural networks. Starting by implementing a simple shallow network and then refining it until a pre-trained ResNet18 is implemented, showing at each step how the accuracy of the model improves. The provided dataset (from [Lazebnik et al., 2006]) contains 15 cate…

Using advanced deep learning techniques on the MNIST dataset. Over 98% validation set accuracy.