Deep_Learning

Description

Solution of deep learning projects.

Lab 1-3 - Neural Networks, Convolutions and Pytorch

Firstly, we work on scalar backpropagation only by numpy and math. And we train on a small dataset - synth dataset to show the inefficiency.

Then, we implement Tensor backpropagation with MNIST dataset to do the image classification.

Problems and Solutions

• Main Problem statement, Solution, Code

Furthermore, we work on custom Automatic differentiation to fully understand how pytorch works.

Problems and Solutions

• Main Problem statement, Solution, Code

Finally, we use pytorch to implement CNNs to do image classification.

Problems and Solutions

• Main Problem statement, Solution, Code

Lab 4 - Recurrent Neural Networks, Autoregressive LSTM

We explore the long-term dependency modelling capabilities of Recurrent Neural Networks (RNNs), Long Short-Term Networks (LSTMs) with Autoregressive. Additionally, we train a character-level language model on natural language text and experiment with character-by-character text generation.

• Main Problem statement, Solution, Code

Lab 5 - Generative Models

We work generative modelling with the variational inference and GAN on the MNIST dataset/Imagenette dataset. We then use variational autoencoders and GAN on the same task and discuss how the intractability issues are resolved. We explore the performance of variational autoencoder and GAN by sampling images from the models.

• Main Problem statement, Solution, Code