Soo Wayne W M, Goudar Vishwa, Wang Xiao-Jing
Department of Engineering, University of Cambridge.
Center for Neural Science, New York University.
bioRxiv. 2023 Oct 10:2023.10.10.561588. doi: 10.1101/2023.10.10.561588.
Training recurrent neural networks (RNNs) has become a go-to approach for generating and evaluating mechanistic neural hypotheses for cognition. The ease and efficiency of training RNNs with backpropagation through time and the availability of robustly supported deep learning libraries has made RNN modeling more approachable and accessible to neuroscience. Yet, a major technical hindrance remains. Cognitive processes such as working memory and decision making involve neural population dynamics over a long period of time within a behavioral trial and across trials. It is difficult to train RNNs to accomplish tasks where neural representations and dynamics have long temporal dependencies without gating mechanisms such as LSTMs or GRUs which currently lack experimental support and prohibit direct comparison between RNNs and biological neural circuits. We tackled this problem based on the idea of specialized skip-connections through time to support the emergence of task-relevant dynamics, and subsequently reinstitute biological plausibility by reverting to the original architecture. We show that this approach enables RNNs to successfully learn cognitive tasks that prove impractical if not impossible to learn using conventional methods. Over numerous tasks considered here, we achieve less training steps and shorter wall-clock times, particularly in tasks that require learning long-term dependencies via temporal integration over long timescales or maintaining a memory of past events in hidden-states. Our methods expand the range of experimental tasks that biologically plausible RNN models can learn, thereby supporting the development of theory for the emergent neural mechanisms of computations involving long-term dependencies.
训练循环神经网络（RNNs）已成为生成和评估认知机制神经假说的常用方法。通过时间反向传播训练RNNs的简便性和效率，以及强大的深度学习库的可用性，使得RNN建模对神经科学来说更易于接近和使用。然而，一个主要的技术障碍仍然存在。诸如工作记忆和决策等认知过程涉及行为试验内以及跨试验的长时间神经群体动态。在没有诸如长短期记忆（LSTM）或门控循环单元（GRU）等门控机制的情况下，训练RNNs完成神经表征和动态具有长时间依赖性的任务是困难的，而目前这些机制缺乏实验支持，并且禁止在RNNs和生物神经回路之间进行直接比较。我们基于通过时间的专门跳跃连接的想法来解决这个问题，以支持与任务相关的动态的出现，随后通过恢复到原始架构来恢复生物合理性。我们表明，这种方法使RNNs能够成功学习认知任务，而使用传统方法学习这些任务即使不是不可能也是不切实际的。在此考虑的众多任务中，我们实现了更少的训练步骤和更短的实际运行时间，特别是在需要通过长时间尺度上的时间积分来学习长期依赖性或在隐藏状态中保持对过去事件的记忆的任务中。我们的方法扩展了具有生物合理性的RNN模型能够学习的实验任务范围，从而支持涉及长期依赖性的计算的新兴神经机制理论的发展。
