Environment setup, jupyter, python, tensor basics with PyTorch
All tutorial materials will be available on this page.
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.
From resnet to mobilenet, guild to efficient CNNs
Descent-based methods, backpropagation, automatic differentiation, bi-level optimization, time-series analysis with CNNs.
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
Generative vs Discriminative models VAE
GAN, WGAN, conditional GAN, styleGAN and more