Introduction to the Course, Introduction to Deep Learning (Boracchi) Slides

From Perceptrons to Feed Forward Neural Networks: the original Perceptron model, Hebbian learning, feed-forward architecture, backpropagation and gradient descent, error functions and maximum likelihood estimation (Matteucci)  Slides

Neural Networks Training: dealing with overfitting (weight decay, early stopping, dropout), vanishing gradient (ReLU and friends), batch normalization (Matteucci)  Slides

The Image Classification Problem  Slides

Convolutional Neural Networks  Slides

CNN Anatomy and Training with Data Scarcity  Slides

Famous CNN architectures Slides

Fully Convolutional CNN and CNN for Semantic Segmentation  Slides

CNN for Localization and CNN Explanations Slides

Object Detction Networks and Metric Learning  Slides

Autoencoders and Generative Adversarial Networks  Slides

Practicals Notebooks and Slides from the exercise sessions held by Loris Giulivi

• Link to Google Drive Folder with all the shared notbooks

Thesis Opportunities related to Deep Learning, Image Analysis / Processing, Computer Vision Thesis Opportunities Description;

Advanced Deep Learning Models And Methods: The Rise of Transformers (Milano, PhD Course organized by Matteo Matteucci and Giacomo Boracchi) January/February 2023 Materials

Advanced Deep Learning Models and Methods (Milano Leonardo, PhD course) February/March 2022 Materials

Mathematical Models And Methods For Image Processing (MMMIP) (Milano Leonardo), Course Materials

Computer Vision (USI Lugano) Spring 2020 ( Materials )

Machine Learning For Non Matrix Data (Milano Leonardo, PhD course) February/March 2019 Materials