Bonus Tutorial: efficient advanced architectures
Material
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 0: Python and PyTorch basics
Environment setup, jupyter, python, tensor basics with PyTorch
Tutorial 1: Supervised Learning
Supervised learning framework, binary and multiclass logistic regression, pytorch and autograd basics
Tutorial 2: Multilayer Perceptron
MLP model, activations, backprop, loss functions and optimization in PyTorch
Tutorial 3: Convolutional Neural Nets
Convolutional and pooling layers, architectures, spatial classification, residual nets.
Tutorial 4: Optimization
A new tutorial about optimization
Tutorial 5: automatic differentiation
automatic differentiation, bi-level optimization
Tutorial 6: Object detection
Evaluation methods (mAP, mIoU), two stage models (RCNN), one stage models (yolo)
Tutorial 7: Transfer learning and domain adaptation
Transfer learning definition and contexts, fine-tuning pre-trained models, unsupervised domain adaptation via an adversarial approach.
Tutorial 8: RNN
RNN, BPTT and TBTT, LSTM and GRU, sentiment analisys and stock prediction.
Tutorial 9: Attention
The attention mechanisem. soft and hard, multiplicative and additive, scaled dot product, attention for alignment translation
Tutorial 10: Transformers
Transformers :)
Tutorial 11: Generative Adverserial Networks
GAN, WGAN, conditional GAN, styleGAN and more
Tutorial 12: Varietional AutoEncoders
Generative vs Discriminative models VAE