Deep Recurrent Neural Network Reveals a Hierarchy of Process Memory during Dynamic Natural Vision

Author:

Shi Junxing,Wen Haiguang,Zhang Yizhen,Han Kuan,Liu Zhongming

Abstract

ABSTRACTThe human visual cortex extracts both spatial and temporal visual features to support perception and guide behavior. Deep convolutional neural networks (CNNs) provide a computational framework to model cortical representation and organization for spatial visual processing, but unable to explain how the brain processes temporal information. To overcome this limitation, we extended a CNN by adding recurrent connections to different layers of the CNN to allow spatial representations to be remembered and accumulated over time. The extended model, or the recurrent neural network (RNN), embodied a hierarchical and distributed model of process memory as an integral part of visual processing. Unlike the CNN, the RNN learned spatiotemporal features from videos to enable action recognition. The RNN better predicted cortical responses to natural movie stimuli than the CNN, at all visual areas especially those along the dorsal stream. As a fully-observable model of visual processing, the RNN also revealed a cortical hierarchy of temporal receptive window, dynamics of process memory, and spatiotemporal representations. These results support the hypothesis of process memory, and demonstrate the potential of using the RNN for in-depth computational understanding of dynamic natural vision.

Publisher

Cold Spring Harbor Laboratory

Reference69 articles.

1. Adolf, D. , Weston, S. , Baecke, S. , Luchtmann, M. , Bernarding, J. , & Kropf, S. (2014). Increasing the reliability of data analysis of functional magnetic resonance imaging by applying a new blockwise permutation method. Frontiers in neuroinformatics, 8.

2. Ballas, N. , Yao, L. , Pal, C. , & Courville, A. (2015). Delving deeper into convolutional networks for learning video representations. arXiv preprint arXiv:1511.06432.

3. Boureau, Y.-L. , Ponce, J. , & LeCun, Y. (2010). A theoretical analysis of feature pooling in visual recognition. Paper presented at the Proceedings of the 27th international conference on machine learning (ICML-10).

4. State-dependent computations: spatiotemporal processing in cortical networks

5. Modeling the hemodynamic response to brain activation

Cited by 3 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