energy-based-models

Training an EBM means shaping an energy landscape so real data sits in valleys, but the intractable partition function blocks plain maximum likelihood. This lesson covers the push-down-push-up principle, contrastive methods (contrastive divergence, noise-contrastive estimation), score matching, and the regularized alternative that avoids sampling entirely.

Why LeCun treats energy as the common language of machine learning. This lesson shows how classification, generative models, self-supervised learning, JEPA, and diffusion all read as energy-based models, ties the contrastive-versus-regularized split back to self-supervised learning, and gives an honest account of where explicit EBMs help and where they do not.

Energy-based models replace input-to-output functions with a scalar energy that scores how compatible a configuration is. This lesson covers the energy function, inference as finding the lowest-energy answer, the energy landscape picture, the link from energy to probability via the partition function, and why this framing handles problems with many valid answers.