Training multilayer neural networks analytically using kernel projection

Huiping Zhuang, Zhiping Lin, Kar Ann Toh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a kernel projection (KP) neural network that analytically determines its network parameters. The proposed network is composed of cascaded modules of 2-layer sub-networks. A technique which encodes the label information into each module has been introduced to enable a locally supervised learning. Such a supervised learning in the 2-layer module begins with a kernel projection in the first layer and determines its parameters analytically via solving a least squares problem in the second layer. We show that the analytic nature of the proposed network allows a learning process significantly faster than that of the traditional backpropagation method as it only needs to visit the dataset once. Experiments of classification tasks on various datasets are carried out, showing comparable or better results compared with several competing methods.

Original languageEnglish
Title of host publication2021 IEEE International Symposium on Circuits and Systems, ISCAS 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728192017
DOIs
Publication statusPublished - 2021
Event53rd IEEE International Symposium on Circuits and Systems, ISCAS 2021 - Daegu, Korea, Republic of
Duration: 2021 May 222021 May 28

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2021-May
ISSN (Print)0271-4310

Conference

Conference53rd IEEE International Symposium on Circuits and Systems, ISCAS 2021
Country/TerritoryKorea, Republic of
CityDaegu
Period21/5/2221/5/28

Bibliographical note

Funding Information:
This work was partially supported by the Science and Engineering Research Council, Agency of Science, Technology and Research, Singapore, through the National Robotics Program under Grant No. 1922500052.

Publisher Copyright:
© 2021 IEEE

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Training multilayer neural networks analytically using kernel projection'. Together they form a unique fingerprint.

Cite this