Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks

Abstract

A long-term goal of AI is to produce agents that can learn a diversity of skills throughout their lifetimes and continuously improve those skills via experience. A longstanding obstacle towards that goal is catastrophic forgetting, which is when learning new information erases previously learned information. Catastrophic forgetting occurs in artificial neural networks (ANNs), which have fueled most recent advances in AI. A recent paper proposed that catastrophic forgetting in ANNs can be reduced by promoting modularity, which can limit forgetting by isolating task information to specific clusters of nodes and connections (functional modules). While the prior work did show that modular ANNs suffered less from catastrophic forgetting, it was not able to produce ANNs that possessed task-specific functional modules, thereby leaving the main theory regarding modularity and forgetting untested. We introduce diffusion-based neuromodulation, which simulates the release of diffusing, neuromodulatory chemicals within an ANN that can modulate (i.e. up or down regulate) learning in a spatial region. On the simple diagnostic problem from the prior work, diffusion-based neuromodulation 1) induces task-specific learning in groups of nodes and connections (task-specific localized learning), which 2) produces functional modules for each subtask, and 3) yields higher performance by eliminating catastrophic forgetting. Overall, our results suggest that diffusion-based neuromodulation promotes task-specific localized learning and functional modularity, which can help solve the challenging, but important problem of catastrophic forgetting.

References in corpus (4)

• Overcoming catastrophic forgetting in neural networks
• Community structure in directed networks
• Progressive Neural Networks
• Evolution of complex modular biological networks

Cited by in corpus (13)

• Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization
• Go-Explore: a New Approach for Hard-Exploration Problems
• Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
• Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents
• Learning to Continually Learn
• Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks
• AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
• Interoceptive robustness through environment-mediated morphological development
• Guiding Neuroevolution with Structural Objectives
• Context Meta-Reinforcement Learning via Neuromodulation
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
• Meta-Learning Bidirectional Update Rules
• Neuromodulated Learning in Deep Neural Networks