Dive into a comprehensive lecture on self-supervised learning and variational inference, presented by renowned speaker Yann LeCun. Explore key concepts including GANs, sparse modeling, amortized inference, and convolutional sparse modeling with group sparsity. Gain insights into discriminant recurrent sparse autoencoders and various self-supervised learning techniques. Examine regularization through temporal consistency and delve into Variational Autoencoders (VAEs), covering both intuitive and probabilistic variational approximation-based interpretations. Enhance your understanding of advanced machine learning concepts in this nearly two-hour session, part of a broader deep learning course series.
Self-Supervised Learning and Variational Inference
Overview
Syllabus
– Welcome to class
– GANs revisited
– Self-supervised learning: a broader purpose
– Sparse modeling
– Amortized inference
– Convolutional sparse modeling with group sparsity
– Discriminant recurrent sparse AE
– Other self-supervised learning techniques
– Group sparsity
– Regularization through temporal consistency
– VAE: intuitive interpretation
– VAE: probabilistic variational approximation-based interpretation
Taught by
Alfredo Canziani
Tags
Related Courses
-
PCA, AE, K-Means, Gaussian Mixture Model, Sparse Coding, and Intuitive VAE
-
Group Sparsity, World Model, and Generative Adversarial Networks
-
Contrastive Methods and Regularised Latent Variable Models
-
Deep Generative Modeling
-
Energy-Based Approaches to Representation Learning - Yann LeCun
-
NYU Deep Learning
