Structured Prediction with Energy Based Models

Structured Prediction with Energy Based Models

Explore structured prediction with energy-based models in this comprehensive lecture by Yann LeCun. Delve into energy-based factor graphs, efficient inference techniques, and sequence labeling. Examine simple energy-based factor graphs with "shallow" factors and the Graph Transformer Net. Compare various loss functions and learn about the application of Viterbi and forward algorithms to graphical transformer networks. Investigate the Lagrangian formulation of backpropagation, neural ODEs, and variational inference for energy-based models. Gain insights into language models as graphs and discover how these concepts apply to real-world machine learning problems.