改进神经网络回放机制，提升记忆重演效率与探索性。
Leakage and Second-Order Dynamics Improve Hippocampal RNN Replay
- 引入隐藏状态泄漏和动量机制，优化噪声递归网络的回放行为。
- 新模型实现压缩时间的回放，速度更快且保持探索能力。
- 适用于研究记忆形成、神经动力学建模的学者与工程师。
生物神经网络（如海马体）可内部生成类似于刺激驱动活动的“回放”。近期计算模型使用噪声递归神经网络（RNN）进行路径积分训练来模拟回放，传统上被描述为朗之万采样，但新方法已超越此框架。本文从采样角度重新审视噪声RNN回放，提出三点改进：(1) 在简化假设下证明回放应遵循的时间变化梯度难以估计，从而支持在RNN中使用隐藏状态泄漏；(2) 验证隐藏状态自适应（负反馈）促进探索，但导致非马尔可夫采样并减缓回放；(3) 首次提出通过隐藏状态动量实现噪声路径积分RNN中的时序压缩回放，其与欠阻尼朗之万采样相关，并结合自适应机制，在维持探索的同时克服了回放迟滞。我们在二维三角形迷宫、T型迷宫及合成大鼠位置细胞活动的高维路径上验证了这些发现。
原文摘要 · Abstract (English)
Biological neural networks (like the hippocampus) can internally generate "replay" resembling stimulus-driven activity. Recent computational models of replay use noisy recurrent neural networks (RNNs) trained to path-integrate. Replay in these networks has been described as Langevin sampling, but new modifiers of noisy RNN replay have surpassed this description. We re-examine noisy RNN replay as sampling to understand or improve it in three ways: (1) Under simple assumptions, we prove that the gradients replay activity should follow are time-varying and difficult to estimate, but readily motivate the use of hidden state leakage in RNNs for replay. (2) We confirm that hidden state adaptation (negative feedback) encourages exploration in replay, but show that it incurs non-Markov sampling that also slows replay. (3) We propose the first model of temporally compressed replay in noisy path-integrating RNNs through hidden state momentum, connect it to underdamped Langevin sampling, and show that, together with adaptation, it counters slowness while maintaining exploration. We verify our findings via path-integration of 2D triangular and T-maze paths and of high-dimensional paths of synthetic rat place cell activity.
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。