Encoding sensory and motor patterns as time-invariant trajectories in recurrent neural networks

Author:

Goudar Vishwa1ORCID,Buonomano Dean V123ORCID

Affiliation:

1. Departments of Neurobiology, University of California, Los Angeles, Los Angeles, United States

2. Integrative Center for Learning and Memory, University of California, Los Angeles, Los Angeles, United States

3. Departments of Psychology, University of California, Los Angeles, Los Angeles, United States

Abstract

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.

Funder

National Science Foundation

Google

National Institutes of Health

Publisher

eLife Sciences Publications, Ltd

Subject

General Immunology and Microbiology,General Biochemistry, Genetics and Molecular Biology,General Medicine,General Neuroscience

Reference66 articles.

1. Tensorflow: Large-scale machine learning on heterogeneous distributed systems;Abadi,2016

2. Building functional networks of spiking model neurons;Abbott;Nature Neuroscience,2016

3. Model of global spontaneous activity and local structured activity during delay periods in the cerebral cortex;Amit;Cerebral Cortex,1997

4. Locomotion controls spatial integration in mouse visual cortex;Ayaz;Current Biology,2013

5. Learning long-term dependencies with gradient descent is difficult;Bengio;IEEE Transactions on Neural Networks,1994

Cited by 66 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3