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

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.

62 pages, 9 figures, submitted to Neural Networks

References in corpus (9)

• A free energy principle for a particular physics
• Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks
• Joint Multimodal Learning with Deep Generative Models
• Deep Probabilistic Programming
• The whole brain architecture approach: Accelerating the development of artificial general intelligence by referring to the brain
• Variational Recurrent Models for Solving Partially Observable Control Tasks
• Shaping Belief States with Generative Environment Models for RL
• lamBERT: Language and Action Learning Using Multimodal BERT
• Canonical Cortical Circuits and the Duality of Bayesian Inference and Optimal Control

Cited by in corpus (3)

• A survey of multimodal deep generative models
• Double Articulation Analyzer with Prosody for Unsupervised Word and Phoneme Discovery
• On Parallelism in Music and Language: A Perspective from Symbol Emergence Systems based on Probabilistic Generative Models