Deep Learning for Artificial Intelligence
DLAI
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.
Architectures such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs) or the Transformer based on Attention mechanisms have shaped a brand new scenario in signal processing. This course will cover the basic principles of deep learning from both an algorithmic and computational perspectives.
DLAI Lectures (2020)
Lecture 1: Machine Learning Basics
Learning Paradigms
Instructor: Xavier Giró-i-Nieto
Lecture 2: The Perceptron
Architectures
Instructor: Xavier Giró-i-Nieto
Lecture 3: Backpropagation
Training
Instructor: Xavier Giró-i-Nieto
Lecture 4: Softmax regression
Architectures
Instructor: Xavier Giró-i-Nieto
Lecture 5: Multi Layer Perceptron
Architectures
Instructor: Xavier Giró-i-Nieto
Lecture 6: Loss functions
Training
Instructor: Javier Ruiz Hidalgo
Lecture 7: Convolutional Neural Networks
Architectures
Instructor: Veronica Vilaplana
Lecture 11: Recurrent Neural Networks
Architectures
Instructor: Xavier Giró-i-Nieto
Lecture 12: Self-supervsed Learning
Learning Paradigms
Instructor: Xavier Giró-i-Nieto
Lecture 13: Generative Adversial Networks
Generative Models
Instructor: Xavier Giró-i-Nieto
Lecture 14: Attention mechanisms
Architectures
Instructor: Xavier Giró-i-Nieto & Marta R. Costa-Jussà
Lecture 15: The Transformer
Architectures
Instructor: Xavier Giró-i-Nieto
Lecture 16: Self-supervised Audio-Visual Learning
Multimodal Learning
Instructor: Xavier Giró-i-Nieto