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)

idl_2021_d1l2_MachineLearning.pdf

Lecture 1.1: Introduction to Machine Learning

Learning Paradigms

Instructor: Elisa Sayrol

idl_2021_d1l3_MultilayerPerceptron.pdf

Lecture 1.2: The Perceptron and Multi-Layer Perceptron

Architectures

Instructor: Elisa Sayrol

idl_2021_d2l1_Backpropagation.pdf

Lecture 2.1: Backpropagation

Training

Instructor: Ramon Morros

idl_2021_d2l2_LossFunctions.pdf

Lecture 2.2: Loss functions

Training

Instructor: Javier Ruiz

idl_2021_d3l1_Optimization.pdf

Lecture 3.1: Optimization

Learning Paradigms

Instructor: Veronica Vilaplana

idl_2021_d4l1_CNN.pdf

Lecture 4.1: Convolutional Neural Networks

Architectures

Instructor: Veronica Vilaplana

idl_2021_d4l2_Architectures.pdf

Lecture 4.2: Architectures

Training

Instructor: Ramon Morros

idl_2021_d5l1_Methodology.pdf

Lecture 5.1: Methodology

Training

Instructor: Javier Ruiz

idl_2021_d5l2_TransferLearning.pdf

Lecture 5.2: Transfer Learning

Learning Paradigms

Instructor: Ramon Morros

idl_2021_d6l1_Interpretability.pdf

Lecture 6.1: Interpretability

Learning Paradigms

Instructor: Marta R. Costa-jussà

idl_2021_d6l2_RNN.pdf

Lecture 6.2: Recurrent Neural Networks - RNNs

Architectures

Instructor: Xavier Giró-i-Nieto

idl_2021_d6l3_Attention.pdf

Lecture 6.3: Attention mechanisms

Architectures

Instructor: Xavier Giró-i-Nieto

idl_2021_d6l4_Transformer.pdf

Lecture 6.4: The Transformer architecture

Architectures

Instructor: Xavier Giró-i-Nieto