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]
 idl_2021_d1l2_MachineLearning.pdf
idl_2021_d1l2_MachineLearning.pdfLearning Paradigms
Instructor: Elisa Sayrol
 idl_2021_d1l3_MultilayerPerceptron.pdf
idl_2021_d1l3_MultilayerPerceptron.pdfArchitectures
Instructor: Elisa Sayrol
 idl_2021_d2l1_Backpropagation.pdf
idl_2021_d2l1_Backpropagation.pdfTraining
Instructor: Ramon Morros
 idl_2021_d2l2_LossFunctions.pdf
idl_2021_d2l2_LossFunctions.pdfTraining
Instructor: Javier Ruiz
 idl_2021_d3l1_Optimization.pdf
idl_2021_d3l1_Optimization.pdfLearning Paradigms
Instructor: Veronica Vilaplana
 idl_2021_d4l1_CNN.pdf
idl_2021_d4l1_CNN.pdfArchitectures
Instructor: Veronica Vilaplana
 idl_2021_d4l2_Architectures.pdf
idl_2021_d4l2_Architectures.pdfTraining
Instructor: Ramon Morros
 idl_2021_d5l1_Methodology.pdf
idl_2021_d5l1_Methodology.pdfTraining
Instructor: Javier Ruiz
 idl_2021_d5l2_TransferLearning.pdf
idl_2021_d5l2_TransferLearning.pdfLearning Paradigms
Instructor: Ramon Morros
 idl_2021_d6l1_Interpretability.pdf
idl_2021_d6l1_Interpretability.pdfLearning Paradigms
Instructor: Marta R. Costa-jussà
 idl_2021_d6l2_RNN.pdf
idl_2021_d6l2_RNN.pdfArchitectures
Instructor: Xavier Giró-i-Nieto
 idl_2021_d6l3_Attention.pdf
idl_2021_d6l3_Attention.pdfArchitectures
Instructor: Xavier Giró-i-Nieto
 idl_2021_d6l4_Transformer.pdf
idl_2021_d6l4_Transformer.pdfArchitectures
Instructor: Xavier Giró-i-Nieto