Introduction to Latent Variable Energy-Based Models: A Path Towards Autonomous Machine Intelligence

Abstract

Current automated systems have crucial limitations that need to be addressed before artificial intelligence can reach human-like levels and bring new technological revolutions. Among others, our societies still lack Level 5 self-driving cars, domestic robots, and virtual assistants that learn reliable world models, reason, and plan complex action sequences. In these notes, we summarize the main ideas behind the architecture of autonomous intelligence of the future proposed by Yann LeCun. In particular, we introduce energy-based and latent variable models and combine their advantages in the building block of LeCun's proposal, that is, in the hierarchical joint embedding predictive architecture (H-JEPA).

23 pages + 1-page appendix, 11 figures. These notes follow the content of three lectures given by Yann LeCun during the Les Houches Summer School on Statistical Physics and Machine Learning in 2022. Feedback and comments are most welcome!

References in corpus (5)

• Bootstrap your own latent: A new approach to self-supervised Learning
• Zero-Shot Text-to-Image Generation
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Energy-based Generative Adversarial Network
• No Language Left Behind: Scaling Human-Centered Machine Translation

Cited by in corpus (2)

• A Prompt-Engineered Large Language Model, Deep Learning Workflow for Materials Classification
• Machine learning the Ising transition: A comparison between discriminative and generative approaches