A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robots

TL;DR

This paper proposes a whole brain probabilistic generative model (WB-PGM) for developing cognitive architectures in developmental robots, aiming for human-like intelligence and continuous learning based on sensory-motor integration.

Contribution

It introduces a novel WB-PGM framework that integrates elemental cognitive modules inspired by the human brain for continuous, developmental learning in robots.

Findings

Development of elemental cognitive modules based on PGMs

Framework for integrating modules for continuous learning

Potential to inform brain science and enhance AI collaboration

Abstract

Building a humanlike integrative artificial cognitive system, that is, an artificial general intelligence (AGI), is the holy grail of the artificial intelligence (AI) field. Furthermore, a computational model that enables an artificial system to achieve cognitive development will be an excellent reference for brain and cognitive science. This paper describes an approach to develop a cognitive architecture by integrating elemental cognitive modules to enable the training of the modules as a whole. This approach is based on two ideas: (1) brain-inspired AI, learning human brain architecture to build human-level intelligence, and (2) a probabilistic generative model(PGM)-based cognitive system to develop a cognitive system for developmental robots by integrating PGMs. The development framework is called a whole brain PGM (WB-PGM), which differs fundamentally from existing cognitive architectures in that it can learn continuously through a system based on sensory-motor information. In this study, we describe the rationale of WB-PGM, the current status of PGM-based elemental cognitive modules, their relationship with the human brain, the approach to the integration of the cognitive modules, and future challenges. Our findings can serve as a reference for brain studies. As PGMs describe explicit informational relationships between variables, this description provides interpretable guidance from computational sciences to brain science. By providing such information, researchers in neuroscience can provide feedback to researchers in AI and robotics on what the current models lack with reference to the brain. Further, it can facilitate collaboration among researchers in neuro-cognitive sciences as well as AI and robotics.