Introduction to latent variable energy-based models: a path toward autonomous machine intelligence
Anna Dawid, Yann LeCun
Abstract
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.
Topics & Concepts
Latent variablePath (computing)Computer scienceVariable (mathematics)Artificial intelligenceLatent variable modelEnergy (signal processing)Statistical physicsMathematicsPhysicsStatisticsProgramming languageMathematical analysisNeural Networks and ApplicationsMachine Learning in Materials ScienceGenerative Adversarial Networks and Image Synthesis