果蝇嗅觉回路机制可提升神经网络持续学习的稳定性与适应性。
Structural features of the fly olfactory circuit mitigate the stability-plasticity dilemma in continual learning
- 基于果蝇嗅觉系统构建可插拔模型，融合现代机器学习方法。
- 在多个挑战性场景中显著提升记忆稳定性和学习灵活性。
- 为低计算成本的持续学习提供生物启发的新思路，适合算法研究者。
人工神经网络在持续学习中面临稳定性-可塑性困境，而大脑能同时保持记忆并维持适应能力。然而，生物体实现持续学习的策略及其对神经网络算法的启示尚不明确。本研究构建了一个最小化的果蝇嗅觉回路模型，探究其支持持续气味学习的生物学机制。提出一种名为Fly Model的可插拔组件，可与现代机器学习方法集成，有效缓解该困境。实验结果表明，该模型在多个具有挑战性的持续学习任务中均显著提升了记忆稳定性与学习可塑性，优于现有策略。果蝇嗅觉系统作为高效的生命学习回路，为机器学习提供了低计算开销的持续学习模块。
原文摘要 · Abstract (English)
Artificial neural networks face the stability-plasticity dilemma in continual learning, while the brain can maintain memories and remain adaptable. However, the biological strategies for continual learning and their potential to inspire learning algorithms in neural networks are poorly understood. This study presents a minimal model of the fly olfactory circuit to investigate the biological strategies that support continual odor learning. We introduce the fly olfactory circuit as a plug-and-play component, termed the Fly Model, which can integrate with modern machine learning methods to address this dilemma. Our findings demonstrate that the Fly Model enhances both memory stability and learning plasticity, overcoming the limitations of current continual learning strategies. We validated its effectiveness across various challenging continual learning scenarios using commonly used datasets. The fly olfactory system serves as an elegant biological circuit for lifelong learning, offering a module that enhances continual learning with minimal additional computational cost for machine learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。