Tutorial 1: Python and tensor basics
Environment setup, jupyter, python, tensor basics with numpy and PyTorch
Tutorials
All tutorial materials will be available on this page.
The tutorial notebooks can be obtained by cloning the course tutorials repo, or viewed in your browser by using nbviewer.
Tutorial 2: Supervised Learning
Supervised learning framework, binary and multiclass logistic regression, pytorch and autograd basics
Tutorial 3: Multilayer Perceptron
MLP model, activations, backprop, loss functions and optimization in PyTorch
Tutorial 4: Convolutional Neural Nets
Convolutional and pooling layers, architectures, spatial classification, residual nets.
Tutorial 5: Optimization
Descent-based methods, backpropagation, automatic differentiation, bi-level optimization, time-series analysis with CNNs.
Tutorial 6: Sequence Models
RNN implementation, sentiment analysis, Temporal Convolution Networks.
Tutorial 7: Attention
Attention mechanisms, sequence-to-sequence models, machine translation.
Tutorial 8: Transfer learning and domain adaptation
Transfer learning definition and contexts, fine-tuning pre-trained models, unsupervised domain adaptation via an adversarial approach.
Tutorial 9: Deep reinforcement learning
The RL setting, openAI Gym, Deep q-learning for Atari games.
Tutorial 10: Geometric deep learning
Filters on graphs, graph convolution layers, semi-supervised node classification
Tutorial 11: CUDA Kernels
The CUDA programming model, numba, implementing CUDA kernels in python, thread synchronization, shared memory