Encoding sensory and motor patterns as time-invariant trajectories in recurrent neural networks
Encoding sensory and motor patterns as time-invariant trajectories in recurrent neural networks
复制标题
DOI：
10.1101/176198
复制
发表时间：
2017-01
期刊：
影响因子：
7.7
通讯作者：
V. Goudar;D. Buonomano
中科院分区：
文献类型：
--
作者：
V. Goudar;D. Buonomano
大脑处理和存储的大部分信息本质上是暂时的——例如，一个口语或一个手写的签名，是由它在时间上如何展开来定义的。然而，神经回路如何编码复杂的时变模式仍不清楚。我们表明，通过调整递归神经网络（RNN）的权重，它可以识别并转录语音数字。该模型阐明了皮层网络中的神经动力学如何解决三个基本挑战：首先，将多个时变的感觉和运动模式编码为稳定的神经轨迹；二是对相关空间特征进行归纳；第三，识别以不同速度播放的相同刺激-我们表明，这种时间不变性之所以出现，是因为循环动态产生具有适当调制角速度的神经轨迹。总之，我们的结果产生了可测试的预测，即循环网络如何使用不同的机制来概括复杂时变刺激的相关空间和时间特征。
Much of the information the brain processes and stores is temporal in nature—a spoken word or a handwritten signature, for example, is defined by how it unfolds in time. However, it remains unclear how neural circuits encode complex time-varying patterns. We show that by tuning the weights of a recurrent neural network (RNN), it can recognize and then transcribe spoken digits. The model elucidates how neural dynamics in cortical networks may resolve three fundamental challenges: first, encode multiple time-varying sensory and motor patterns as stable neural trajectories; second, generalize across relevant spatial features; third, identify the same stimuli played at different speeds—we show that this temporal invariance emerges because the recurrent dynamics generate neural trajectories with appropriately modulated angular velocities. Together our results generate testable predictions as to how recurrent networks may use different mechanisms to generalize across the relevant spatial and temporal features of complex time-varying stimuli.