Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference
Preprint
Abstract
Current AI systems achieve impressive performance on many tasks, yet they lack core attributes of biological intelligence, including rapid, continual learning, representations grounded in sensorimotor interactions, and structured knowledge that enables efficient generalization. Neuroscience theory suggests that mammals evolved flexible intelligence through the replication of a semi-independent, sensorimotor module, a functional unit known as a cortical column. To address the disparity between biological and artificial intelligence, thousand-brains systems were proposed as a means of mirroring the architecture of cortical columns and their interactions. 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. These representations include an emphasis on classifying objects by their global shape, as well as a natural ability to detect object symmetries. We then explore Monty's use of model-free and model-based policies to enable rapid inference by supporting principled movements. We find that such policies complement Monty's modular architecture, a design that can accommodate communication between modules to further accelerate inference speed via a novel `voting' algorithm. Finally, we examine Monty's use of associative, Hebbian-like binding to enable rapid, continual, and computationally efficient learning, properties that compare favorably to current deep learning architectures. While Monty is still in a nascent stage of development, these findings support thousand-brains systems as a powerful and promising new approach to AI.Keywords
All Related Versions
This publication has 59 references indexed in Scilit:
- The Tolman-Eichenbaum Machine: Unifying Space and Relational Memory through Generalization in the Hippocampal FormationCell, 2020
- A Computational Model of Visual Recognition Memory via Grid CellsCurrent Biology, 2019
- Theories of Error Back-Propagation in the BrainTrends in Cognitive Sciences, 2019
- Corticofugal circuits: Communication lines from the cortex to the rest of the brainJournal of Comparative Neurology, 2018
- Revisiting active perceptionAutonomous Robots, 2017
- First Steps Towards an Intelligent Laser Welding Architecture Using Deep Neural Networks and Reinforcement LearningProcedia Technology, 2014
- Untangling invariant object recognitionTrends in Cognitive Sciences, 2007
- A model of grounded language acquisition: Sensorimotor features improve lexical and grammatical learningJournal of Memory and Language, 2005
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in positionBiological Cybernetics, 1980
- Uniformity of monkey striate cortex: A parallel relationship between field size, scatter, and magnification factorJournal of Comparative Neurology, 1974