Papers
The Thousand Brains Theory 2.0: An Extension for the Long-Range Connections of the Neocortical Heterarchy
In the traditional understanding of the neocortex, sensory information flows up a hierarchy of regions, with each level processing increasingly complex features. Information also flows down the hierarchy via a different set of connections. Although the hierarchical model has significant support, many anatomical connections do not conform to the standard hierarchical interpretation. This paper proposes a theory explaining their function…
AUTHORS:
Charmaine Lai
PUBLICATION:
Neural Computation
Two Years of the Thousand Brains Project: What We Accomplished and Where We Are Today
The Thousand Brains Project (TBP) has been around for about two years now, and a lot has happened since we started. The following report will recap all the exciting progress we have made since then and provide a high-level overview of our direction.
AUTHORS:
tbpadminflywheel
PUBLICATION:
Our Website
Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning & Inference
In the current work, we evaluate the unique properties of Monty, the first implementation of a thousand-brains system. We focus on 3D object perception, and in particular, the combined task of object recognition and pose estimation. Utilizing the YCB dataset of household objects, we first assess Monty’s use of sensorimotor learning to build structured representations, finding that these enable robust generalization…
AUTHORS:
Charmaine Lai
PUBLICATION:
Neural Computation
The Thousand Brains Project: A New Paradigm for Sensorimotor Intelligence
This paper reviews the state of artificial intelligence (AI) and the quest to create general AI with human-like cognitive capabilities. This review argues that improvements in current AI using mathematical or logical techniques are unlikely to lead to general AI. Instead, the AI community should incorporate neuroscience discoveries about the neocortex. It further explains the limitations of current AI techniques and focuses on the biologically constrained Thousand Brains Theory describing the neocortex’s computational principles.
AUTHORS:
Charmaine Lai
PUBLICATION:
arXiv
A Thousand Brains: Toward Biologically Constrained AI
This paper reviews the state of artificial intelligence (AI) and the quest to create general AI with human-like cognitive capabilities. This review argues that improvements in current AI using mathematical or logical techniques are unlikely to lead to general AI. Instead, the AI community should incorporate neuroscience discoveries about the neocortex. It further explains the limitations of current AI techniques and focuses on the biologically constrained Thousand Brains Theory describing the neocortex’s computational principles.
AUTHORS:
Charmaine Lai
PUBLICATION:
Springer Nature
A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex
In this research paper, Numenta proposes a novel theoretical framework for understanding what the neocortex does and how it does it. The framework is based on grid cells and has significant implications for neuroscience and machine intelligence.
AUTHORS:
Charmaine Lai
PUBLICATION:
Frontiers in Neural Circuits