The Thousand Brains Project: A New Paradigm for Sensorimotor Intelligence
Viviane Clay, Niels Leadholm, Jeff Hawkins

TL;DR
The Thousand Brains Project proposes a new AI paradigm inspired by neocortical principles, emphasizing rapid, associative learning through modular cortical-like units to achieve flexible, human-like sensorimotor intelligence.
Contribution
It introduces a novel, cortical-inspired architecture with semi-independent modules that model objects and learn quickly, enabling versatile and continual learning in AI systems.
Findings
Early prototype demonstrates rapid object learning.
Modules interact hierarchically and non-hierarchically.
Supports multimodal and abstract representations.
Abstract
Artificial intelligence has advanced rapidly in the last decade, driven primarily by progress in the scale of deep-learning systems. Despite these advances, the creation of intelligent systems that can operate effectively in diverse, real-world environments remains a significant challenge. In this white paper, we outline the Thousand Brains Project, an ongoing research effort to develop an alternative, complementary form of AI, derived from the operating principles of the neocortex. We present an early version of a thousand-brains system, a sensorimotor agent that is uniquely suited to quickly learn a wide range of tasks and eventually implement any capabilities the human neocortex has. Core to its design is the use of a repeating computational unit, the learning module, modeled on the cortical columns found in mammalian brains. Each learning module operates as a semi-independent unit…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsEEG and Brain-Computer Interfaces · Neuroscience, Education and Cognitive Function
