Skip to main content

What are energy based models good for?

Difficulty level

This panel discussion covers how energy based models are used and is a part of the Deep Learning Course at CDS, a course that covered the latest techniques in deep learning and representation learning, focusing on supervised and unsupervised deep learning, embedding methods, metric learning, convolutional and recurrent nets, with applications to computer vision, natural language understanding, and speech recognition. Prerequisites for this course include: Introduction to Deep LearningParameter sharing, and Introduction to Data Science or a Graduate Level Machine Learning.

Topics covered in this lesson


00:00 – Energy interpretation of classifiers
02:10 – Self-supervised learning
05:00 – Video compression as latent collection
06:38 – Joint embeddings as contrastive method
08:12 – Interpolation and extrapolation