12 Days of Christmas - Day 12: Insights
Yann LeCun: A Path Towards Autonomous Machine Intelligence
Courant Institute of Mathematical Sciences, New York University
Meta - Fundamental AI Research
ACM Turing Award Laureate
In his paper from June 2022, Yann LeCun proposed an architecture and training paradigms with which to construct autonomous intelligent agents. It combines concepts such as configurable predictive world model, behavior driven through intrinsic motivation, and hierarchical joint embedding architectures trained with self-supervised learning.
The position paper expresses Yann's vision for a path towards intelligent machines that learn more like animals and humans, that can reason and plan, and whose behavior is driven by intrinsic objectives, rather than by hard-wired programs, external supervision, or external rewards. In doing so, Yann proposes an architecture for intelligent agents with possible solutions to all three challenges of:
- How can machines learn to represent the world, learn to predict, and learn to act largely by observation?
- How can machine reason and plan in ways that are compatible with gradient-based learning?
- How can machines learn to represent percepts and action plans in a hierarchical manner, at multiple levels of abstraction, and multiple time scales?
Paper: A Path Towards Autonomous Machine Intelligence Version 0.9.2, 2022-06-27
Read the paper (PDF) here
Video: Yann LeCun: From Machine Learning to Autonomous Intelligence (UC Berkeley EECS Colloquium - 27 September 2022)