A brain basis of dynamical intelligence for AI and computational neuroscience

TL;DR

This paper advocates for integrating brain-inspired dynamical principles, such as neural synchrony and oscillations, into AI and neuroscience to develop more brain-like, efficient, and adaptable intelligent systems.

Contribution

It introduces a dynamical framework emphasizing neural timing, structure, and interaction, fostering collaboration between AI and computational neuroscience for advancing intelligent systems.

Findings

Neural synchrony and oscillations as computational layers

Hierarchical models updated through neural dynamics

Agent-centered paradigms accelerate understanding of intelligence

Abstract

The deep neural nets of modern artificial intelligence (AI) have not achieved defining features of biological intelligence, including abstraction, causal learning, and energy-efficiency. While scaling to larger models has delivered performance improvements for current applications, more brain-like capacities may demand new theories, models, and methods for designing artificial learning systems. Here, we argue that this opportunity to reassess insights from the brain should stimulate cooperation between AI research and theory-driven computational neuroscience (CN). To motivate a brain basis of neural computation, we present a dynamical view of intelligence from which we elaborate concepts of sparsity in network structure, temporal dynamics, and interactive learning. In particular, we suggest that temporal dynamics, as expressed through neural synchrony, nested oscillations, and flexible sequences, provide a rich computational layer for reading and updating hierarchical models distributed in long-term memory networks. Moreover, embracing agent-centered paradigms in AI and CN will accelerate our understanding of the complex dynamics and behaviors that build useful world models. A convergence of AI/CN theories and objectives will reveal dynamical principles of intelligence for brains and engineered learning systems. This article was inspired by our symposium on dynamical neuroscience and machine learning at the 6th Annual US/NIH BRAIN Initiative Investigators Meeting.