Tutorial 1: Python, numpy and friends 🐍
Environment setup, jupyter, python and numpy basics
Tutorials
All tutorial materials are available from the course tutorials repo. We recommend cloning this repo and pulling updates from it if you want to run the notebooks yourself.
Additionally, the tutorial notebooks can be viewed in your browser by using nbviewer.
Tutorial 1: Python,
Tutorial 2: Logistic regression
Supervised learning context, binary and multiclass logistic regression
Tutorial 3: Intro to CNNs
MLPs, convolutional layers, loss functions and optimization in PyTorch
Tutorial 4: Training Neural Networks
Overfitting and regularization, dropout, batch normalization, learning rate decay, momentum, adaptive optimizers, training practices.
Tutorial 5: Convolutional Neural Nets
Convolutional and pooling layers, architectures, spatial classification, residual nets.
Tutorial 6: RNNs
Word representations, vanilla RNNs, GRUs, LSTM, attention.
Tutorial 7: Unsupervised learning and GANs
Autoencoders: denoising, deep and variational, generative adversarial networks.
Tutorial 8: Domain Adaptation
Unsupervised vs. supervised approach, approximate labels, AutoDIAL.
Tutorial 10: CUDA with numba
Numba, CUDA programming model, writing CUDA kernels in python.
Tutorial 11: DNN Compression
Number representation, pruning, bottlenecks, quantization.