All tutorial materials will be available on this page.
Environment setup, jupyter, python, tensor basics with PyTorch
Supervised learning framework, binary and multiclass logistic regression, pytorch and autograd basics
MLP model, activations, backprop, loss functions and optimization in PyTorch
Convolutional and pooling layers, architectures, spatial classification, residual nets.
A new tutorial about optimization
automatic differentiation, bi-level optimization
Evaluation methods (mAP, mIoU), two stage models (RCNN), one stage models (yolo)
Transfer learning definition and contexts, fine-tuning pre-trained models, unsupervised domain adaptation via an adversarial approach.
RNN, BPTT and TBTT, LSTM and GRU, sentiment analisys and stock prediction.
The attention mechanisem. soft and hard, multiplicative and additive, scaled dot product, attention for alignment translation
GAN, WGAN, conditional GAN, styleGAN and more
Generative vs Discriminative models VAE