Lateral interaction by Laplacian‐based graph smoothing for deep neural networks

Author:

Chen Jianhui123ORCID,Wang Zuoren145ORCID,Liu Cheng‐Lin23

Affiliation:

1. Institute of Neuroscience State Key Laboratory of Neuroscience Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China

2. State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of Chinese Academy of Sciences Beijing China

3. University of Chinese Academy of Sciences Beijing China

4. School of Future Technology University of Chinese Academy of Sciences Beijing China

5. School of Life Science and Technology ShanghaiTech University Shanghai China

Abstract

AbstractLateral interaction in the biological brain is a key mechanism that underlies higher cognitive functions. Linear self‐organising map (SOM) introduces lateral interaction in a general form in which signals of any modality can be used. Some approaches directly incorporate SOM learning rules into neural networks, but incur complex operations and poor extendibility. The efficient way to implement lateral interaction in deep neural networks is not well established. The use of Laplacian Matrix‐based Smoothing (LS) regularisation is proposed for implementing lateral interaction in a concise form. The authors’ derivation and experiments show that lateral interaction implemented by SOM model is a special case of LS‐regulated k‐means, and they both show the topology‐preserving capability. The authors also verify that LS‐regularisation can be used in conjunction with the end‐to‐end training paradigm in deep auto‐encoders. Additionally, the benefits of LS‐regularisation in relaxing the requirement of parameter initialisation in various models and improving the classification performance of prototype classifiers are evaluated. Furthermore, the topologically ordered structure introduced by LS‐regularisation in feature extractor can improve the generalisation performance on classification tasks. Overall, LS‐regularisation is an effective and efficient way to implement lateral interaction and can be easily extended to different models.

Funder

National Natural Science Foundation of China

Publisher

Institution of Engineering and Technology (IET)

Subject

Artificial Intelligence,Computer Networks and Communications,Computer Vision and Pattern Recognition,Human-Computer Interaction,Information Systems

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