Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanism

2025-04-08

AI Summary

Existing AI models exhibit exponential growth in parameters and energy consumption as cognitive capabilities increase, suffering from redundancy and poor scalability for continual multi-task learning—unlike the human brain, which develops complex cognition incrementally and efficiently. Method: Inspired by cross-regional sequential neurodevelopment in the brain, we propose a Progressive Cognitive Enhancement (PCE) framework for Perception-Motor-Interaction (PMI) tasks. It introduces two novel, synergistic mechanisms: (i) temporal-development-driven long-range connection evolution, and (ii) feedback-guided local connection suppression and structured pruning. Contribution/Results: The framework achieves significant model compression and energy reduction without replay, regularization, or parameter freezing. In continual learning settings, it outperforms direct-learning baselines in task accuracy while maintaining biological plausibility. Empirical results validate its efficacy as a low-power, scalable, and generalizable pathway toward biologically inspired cognitive enhancement.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Life-Long and Continual Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Cognitive functions in current artificial intelligence networks are tied to the exponential increase in network scale, whereas the human brain can continuously learn hundreds of cognitive functions with remarkably low energy consumption. This advantage is in part due to the brain cross-regional temporal development mechanisms, where the progressive formation, reorganization, and pruning of connections from basic to advanced regions, facilitate knowledge transfer and prevent network redundancy. Inspired by these, we propose the Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanism(TD-MCL), enabling cognitive enhancement from simple to complex in Perception-Motor-Interaction(PMI) multiple cognitive task scenarios. The TD-MCL model proposes the sequential evolution of long-range connections between different cognitive modules to promote positive knowledge transfer, while using feedback-guided local connection inhibition and pruning to effectively eliminate redundancies in previous tasks, reducing energy consumption while preserving acquired knowledge. Experiments show that the proposed method can achieve continual learning capabilities while reducing network scale, without introducing regularization, replay, or freezing strategies, and achieving superior accuracy on new tasks compared to direct learning. The proposed method shows that the brain's developmental mechanisms offer a valuable reference for exploring biologically plausible, low-energy enhancements of general cognitive abilities.

Problem

• Enables continual learning of multiple cognitive functions efficiently
• Reduces network redundancy and energy consumption in AI
• Mimics brain's temporal development for knowledge transfer

Innovation

• Brain-inspired temporal development mechanism for learning
• Sequential evolution of long-range cognitive connections
• Feedback-guided local connection inhibition and pruning