Introduction to Deep Learning
IDL
Topics covered:Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features.
This is a short course (based on 4 lectures) that will cover the basic principles of deep learning.
The previous course webpage can be found: [2021], [2020], [2019], [2018]
lDL Lectures (2022)
Lecture 1.1: Introduction to Machine Learning
Learning Paradigms
Instructor: Elisa Sayrol
Lecture 1.2: The Perceptron and Multi-Layer Perceptron
Architectures
Instructor: Elisa Sayrol
Lecture 2.1: Backpropagation
Training
Instructor: Ramon Morros
Lecture 2.2: Loss functions
Training
Instructor: Javier Ruiz
Lecture 3.1: Optimization
Learning Paradigms
Instructor: Veronica Vilaplana
Lecture 4.1: Convolutional Neural Networks
Architectures
Instructor: Veronica Vilaplana
Lecture 4.2: Architectures
Training
Instructor: Ramon Morros
Lecture 5.1: Methodology
Training
Instructor: Javier Ruiz
Lecture 5.2: Transfer Learning
Learning Paradigms
Instructor: Ramon Morros
Lecture 6.1: Interpretability
Learning Paradigms
Instructor: Marta R. Costa-jussà
Lecture 6.2: Recurrent Neural Networks - RNNs
Architectures
Instructor: Xavier Giró-i-Nieto
Lecture 6.3: Attention mechanisms
Architectures
Instructor: Xavier Giró-i-Nieto
Lecture 6.4: The Transformer architecture
Architectures
Instructor: Xavier Giró-i-Nieto