Study on general Second-Order Neural Units (SONUs)

Noriyasu Homma, Madan M. Gupta

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

1 Citation (Scopus)

Abstract

In this paper, a general second-order neural unit (SONU) is developed using a new matrix form which can provide a general second-order combination of the input signals and the synaptic weights. It is shown that, from the point of view of both the neural computing process and its learning algorithm, the linear combination neural units used widely in multilayered neural networks are only a subset of the proposed SONUs. Simulation studies for both the pattern classification and function approximation problems demonstrate that the learning and generalization abilities of the proposed SONUs are much superior to that of the linear combination neural units.

Original languageEnglish
Title of host publicationMultimedia, Image Processing and Soft Computing
Subtitle of host publicationTrends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002
Pages177-182
Number of pages6
Publication statusPublished - 2002 Dec 1
Event4th International Symposium on Soft Computing for Industry, ISSCI 2002 and the 3rd International Forum on Multimedia and Image Processing, IFMIP 2002, Held within the World Automation Congress, WAC 2002 - Orlando, FL, United States
Duration: 2002 Jun 92002 Jun 13

Publication series

NameMultimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002
Volume13

Other

Other4th International Symposium on Soft Computing for Industry, ISSCI 2002 and the 3rd International Forum on Multimedia and Image Processing, IFMIP 2002, Held within the World Automation Congress, WAC 2002
CountryUnited States
CityOrlando, FL
Period02/6/902/6/13

Keywords

  • Classification
  • Function approximation
  • Learning algorithms
  • Neural networks
  • Second-order systems

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint Dive into the research topics of 'Study on general Second-Order Neural Units (SONUs)'. Together they form a unique fingerprint.

Cite this