当前位置:科学网首页 > 小柯机器人 >详情
利用共享动态基序在循环网络中进行灵活的多任务计算
作者:小柯机器人 发布时间:2024/7/13 22:30:36

美国斯坦福大学Laura N. Driscoll等共同合作,近期取得重要工作进展。他们研究利用共享动态基序在循环网络中进行灵活的多任务计算。相关研究成果2024年7月9日在线发表于《自然—神经科学》杂志上。

据介绍,灵活的计算是智能行为的标志。然而,人们对于神经网络如何在不同计算环境中重新配置以进行不同的计算目前还不清楚。

研究人员通过对多任务人工递归神经网络的研究,确定了一种用于模块计算的算法神经基底。动态系统分析揭示了学习的计算策略反映了训练任务集的模块化子任务结构。动态基序是通过动力学实现特定计算的神经活动的重复模式,如吸引子、决策边界和旋转,在任务中重复使用。例如,需要连续圆形变量内存的任务会重新利用相同的环形吸引子。

研究人员证明了当单元激活函数被限制为正时,动态基序是由单元簇实现的。集群病变导致模块化性能缺陷。在最初的学习阶段后,对基序进行了重新配置,以实现快速迁移学习。

总之,这一工作将动态基序确立为组成计算的基本单元,介于神经元和网络之间。由于全脑研究同时记录多个专门系统的活动,动态基序框架将指导有关专门化和泛化的问题。

附:英文原文

Title: Flexible multitask computation in recurrent networks utilizes shared dynamical motifs

Author: Driscoll, Laura N., Shenoy, Krishna, Sussillo, David

Issue&Volume: 2024-07-09

Abstract: Flexible computation is a hallmark of intelligent behavior. However, little is known about how neural networks contextually reconfigure for different computations. In the present work, we identified an algorithmic neural substrate for modular computation through the study of multitasking artificial recurrent neural networks. Dynamical systems analyses revealed learned computational strategies mirroring the modular subtask structure of the training task set. Dynamical motifs, which are recurring patterns of neural activity that implement specific computations through dynamics, such as attractors, decision boundaries and rotations, were reused across tasks. For example, tasks requiring memory of a continuous circular variable repurposed the same ring attractor. We showed that dynamical motifs were implemented by clusters of units when the unit activation function was restricted to be positive. Cluster lesions caused modular performance deficits. Motifs were reconfigured for fast transfer learning after an initial phase of learning. This work establishes dynamical motifs as a fundamental unit of compositional computation, intermediate between neuron and network. As whole-brain studies simultaneously record activity from multiple specialized systems, the dynamical motif framework will guide questions about specialization and generalization.

DOI: 10.1038/s41593-024-01668-6

Source: https://www.nature.com/articles/s41593-024-01668-6

期刊信息

Nature Neuroscience:《自然—神经科学》,创刊于1998年。隶属于施普林格·自然出版集团,最新IF:28.771
官方网址:https://www.nature.com/neuro/
投稿链接:https://mts-nn.nature.com/cgi-bin/main.plex