Deep Learning with PyTorch: Zero to GANs

• Introduction to Jupyter notebooks & Data Science in Python
• Creating vectors, matrices & Tensors in PyTorch
• Tensor operations and gradient computations
• Interoperability of PyTorch with Numpy
• Linear Regression from scratch using Tensor operations
• Weights, biases and the mean squared error loss function
• Gradient descent and model training with PyTorch Autograd
• Linear Regression using PyTorch built-ins (nn.Linear, nn.functional etc.)

The objective of this assignment is to develop a solid understanding of PyTorch tensors. In this assignment you will:

• Pick 5 interesting functions related to PyTorch tensors by reading the documentation
• Create a Jupyter notebook using a starter template to illustrate their usage, and share them using Jovian(Optional)
• Write a blog post to accompany and showcase your Jupyter notebook(Optional)
• Share your work with the community and exchange feedback with other participants

• Working with images from the MNIST dataset
• Training and validation dataset creation
• Softmax function and categorical cross entropy loss
• Model training, evaluation and sample predictions

In this assignment, we’re going to use information like a person’s age, sex, BMI, no. of children, and smoking habit to predict the price of yearly medical bills. We will train a model with the following steps:

• Download and explore the dataset
• Prepare the dataset for training
• Create a linear regression model
• Train the model to fit the data
• Make predictions using the trained model

• Working with cloud GPU platforms like Kaggle & Colab
• Creating a multilayer neural network using nn.Module
• Activation function, non-linearity and universal approximation theorem
• Moving with datasets and models to the GPU for faster training

The ability to try many different neural network architectures to address a problem is what makes deep learning really powerful, especially compared to shallow learning techniques like linear regression, logistic regression etc. In this assignment, you will:

• Explore the CIFAR10 dataset
• Set up a training pipeline to train a neural network on a GPU
• Experiment with different network architectures & hyperparameters

• Working with the 3-channel RGB images from the CIFAR10 dataset
• Introduction to Convolutions, kernels & features maps
• Underfitting, overfitting and techniques to improve model performance

Students will participate in a private data science competition hosted on the Kaggle platform. The competition will run for 3 weeks, allowing students to apply & improve their skills in a competitive environment. Students will gain exposure to working with cloud GPU platforms.

• Improving the dataset using data normalization and data augmentation
• Improving the model using residual connections and batch normalization
• Improving the training loop using learning rate annealing, weight decay and gradient clip
• Training a state of the art image classifier from scratch in 10 minutes

• Introduction to generative modeling and application of GANs
• Creating generator and discriminator neural networks
• Generating and evaluating fake images of handwritten digits
• Training the generator and discriminator in tandem and visualizing results

For the course project, students will create an image classification model using Convolutional neural networks, on a real-world dataset of their choice. The project will allow students to experiment with different types of models and regularization techniques. Students will also present their work at the end of the course and publish a blog post describing their approach and results.