CSE6250BDH-LAB-DL

GT CSE6250 Big Data Analytics for Healthcare - Deep Learning Lab Sessions

Maintained by Sungtae An [email protected]

In this series of tutorials, we will learn how to implement a varity of Neural Networks by using PyTorch with the example problems of healthcare domain.

The contents are as follows:

0. Intro to PyTorch
   • Pytorch Tensor
   • Converting between Tensor and ndarray (Numpy)
   • Indexing and Math operations
   • GPU Acceleration
   • Automatic differentiation with Variable
1. Feed-forward Neural Networks
   • Basic usage of TensorDataset and DataLoader in Pytorch
   • How to define a python class to construct neural network
   • Loss function and Optimizer
   • Basic trining iteration
2. Convolutional Neural Networks
   • How to construct a class of ConvNet with convolutional layers, pooling layers, and fully-connected layers.
   • How to use PyTorch on GPU
   • Difference between train mode and eval mode
3. Recurrent Neural Networks
   • Preparing data in a proper shape for RNN
   • How to use Recurrent Layer modules in PyTorch
4. Advanced Topics
   • Coming Soon