2022 APathTowardsAutonomousMachineIn
- (LeCun, 2022) ⇒ Yann LeCun. (2022). “A Path Towards Autonomous Machine Intelligence.”
Subject Headings: Physical World Foundation Model.
Notes
Cited By
Quotes
Abstract
How could machines learn as efficiently as humans and animals? How could machines learn to reason and plan? How could machines learn representations of percepts and action plans at multiple levels of abstraction, enabling them to reason, predict, and plan at multiple time horizons? This position paper proposes an architecture and training paradigms with which to construct autonomous intelligent agents. It combine concepts such as configurable predictive world model, behavior-driven through intrinsic motivation, and hierarchical joint embedding architectures trained with self-supervised learning.
Keywords: Artificial Intelligence, Machine Common Sense, Cognitive Architecture, Deep Learning, Self-Supervised Learning, Energy-Based Model, World Models, Joint Embedding Architecture, Intrinsic Motivation.
References
;
| Author | volume | Date Value | title | type | journal | titleUrl | doi | note | year | |
|---|---|---|---|---|---|---|---|---|---|---|
| 2022 APathTowardsAutonomousMachineIn | Yann LeCun | A Path Towards Autonomous Machine Intelligence | 2022 |