A brain basis of dynamical intelligence for AI and computational neuroscience

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.

arXiv commentPerspective article: 24 pages, 3 figures, 1 display box

References in corpus (16)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Language Models are Few-Shot Learners
• Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition
• Untangling cross-frequency coupling in neuroscience
• Deep learning tools for the measurement of animal behavior in neuroscience
• Linking connectivity, dynamics and computations in low-rank recurrent neural networks
• The Unreasonable Effectiveness of Deep Learning in Artificial Intelligence
• Exploration by Random Network Distillation
• Agent57: Outperforming the Atari Human Benchmark
• On the role of theory and modeling in neuroscience
• BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning
• Pruning neural networks without any data by iteratively conserving synaptic flow
• How Can We Be So Dense? The Benefits of Using Highly Sparse Representations
• Cognitive swarming in complex environments with attractor dynamics and oscillatory computing
• Activation Relaxation: A Local Dynamical Approximation to Backpropagation in the Brain
• Exploring Exploration: Comparing Children with RL Agents in Unified Environments