Info about practicals

Course 1
Computer Vision and ML basics: Visual (local) feature detection and description, Bag of Word Image representation, Linear classification (SVM)

Course 2
Introduction to Neural Networks (NNs)

Course 3
Machine Learning basics (2): (done on the blackboard) statistical decision theory and Risk minimization, ERM and regularization, connection with weight decay and maximizing the margin in SVM;
End of slides on Datasets, benchmarks and evaluation; commented examples

Course 4
Neural Nets for Image Classification

Course 5
Neural Nets for Image Classification
Vision Transformers

Course 6: Segmentation with CNN and with Transformers (and detection)

Course 7 Transfer learning and Domain adaptation

Course 8
Generative models with GANs

Course 9
Conditional GANs and diffusions models

Course 10 Control at 2pm! (all the content explained in course, not the practicals, no documents allowed)

Course 11
Introduction to foundation models: Transformers, CLIP-based Xmodal retrieval, Editing with diffusion models, Flamingo.

Course 12/13 Bayesian deep learning

Course 14 Robustness

Further reading (available at SorbonneU library):
Book Pattern Recognition and Machine Learning, C. M. Bishop
Book Deep Learning, I. Goodfellow, Y. Bengio, A. Courville
Book Computer Vision: Algorithms and Applications, Richard Szeliski