Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planning
Rao, Rajesh P. N., Gklezakos, Dimitrios C., Sathish, Vishwas
–arXiv.org Artificial Intelligence
Predictive coding has emerged as a prominent model of how the brain learns through predictions, anticipating the importance accorded to predictive learning in recent AI architectures such as transformers. Here we propose a new framework for predictive coding called active predictive coding which can learn hierarchical world models and solve two radically different open problems in AI: (1) how do we learn compositional representations, e.g., part-whole hierarchies, for equivariant vision? and (2) how do we solve large-scale planning problems, which are hard for traditional reinforcement learning, by composing complex action sequences from primitive policies? Our approach exploits hypernetworks, self-supervised learning and reinforcement learning to learn hierarchical world models that combine task-invariant state transition networks and task-dependent policy networks at multiple abstraction levels. We demonstrate the viability of our approach on a variety of vision datasets (MNIST, FashionMNIST, Omniglot) as well as on a scalable hierarchical planning problem. Our results represent, to our knowledge, the first demonstration of a unified solution to the part-whole learning problem posed by Hinton, the nested reference frames problem posed by Hawkins, and the integrated state-action hierarchy learning problem in reinforcement learning.
arXiv.org Artificial Intelligence
Oct-23-2022
- Country:
- Europe > France (0.04)
- North America
- Genre:
- Research Report > New Finding (0.48)
- Industry:
- Law > Litigation (1.00)
- Health & Medicine > Therapeutic Area
- Neurology (0.68)
- Education > Focused Education
- Special Education (0.45)
- Technology: