Introduction to Deep Learning & Neural Networks

About

This repository contains

Chapter	Assignment	Description
#1	Train linear classifier	Train a linear classifier with dummy input values.
#2	Train a Neural Network	Train a neural network to classify CIFAR10 images into one of the 10 classes.
#3	Build and Train CNN	Build and train CNN on CIFAR dataset. This assignment is a follow-up of previous assignment (Chapter #2). Here feedforward network is replaced by CNN.
#3	Batch Normalization	Batch normalization function
#3	Skip Connection	ResNet skip connection class
#4	LSTM cell	Develop an LSTM cell from scratch.
#4	RNN	RNN
#5	Autoencoder	Filter size computed from the equation for number of parameters.
#5	ELBO	Evidence lower bound (ELBO)
#5	Reparameterization trick	Reparameterization trick
#6	GAN	Generative Adversarial Network
#7	Transformer Encoder	A simple transformer encoder
#8	Graph Laplacian	Graph Laplacian
#8	Spectral Image Segmentation	Spectral Image Segmentation with Graph Laplacian
#8	Chebyshev approximation	Chebyshev approximation for the Laplacian powers
#8	GCN	1-hop Graph Convolutional Network

Deep Learning PyTorch Fundamentals
- Explains the basics of PyTorch model training using a simple regression and a classification problem.
- The steps involved in the training process are better explained in this course.
Natural Language Processing with Deep Learning (CS224n)
- Stanford University course by Prof. Christopher Manning
- The repository contains my assignment solutions.