Study on general Second-Order Neural Units (SONUs)

Noriyasu Homma; Madan M. Gupta

Study on general Second-Order Neural Units (SONUs)

Noriyasu Homma, Madan M. Gupta

MED - Health Sciences

University of Saskatchewan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

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 language	English
Title of host publication	Multimedia, Image Processing and Soft Computing
Subtitle of host publication	Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002
Pages	177-182
Number of pages	6
Publication status	Published - 2002
Event	4th 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 9 → 2002 Jun 13

Publication series

Name	Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002
Volume	13

Conference

Conference	4th 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
Country/Territory	United States
City	Orlando, FL
Period	02/6/9 → 02/6/13

Keywords

Classification
Function approximation
Learning algorithms
Neural networks
Second-order systems

Cite this

Homma, N., & Gupta, M. M. (2002). Study on general Second-Order Neural Units (SONUs). In Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002 (pp. 177-182). (Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002; Vol. 13).

Homma, Noriyasu ; Gupta, Madan M. / Study on general Second-Order Neural Units (SONUs). Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002. 2002. pp. 177-182 (Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002).

@inproceedings{4c67b06ac6ae40c3a05207e4d3ab7c35,

title = "Study on general Second-Order Neural Units (SONUs)",

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.",

keywords = "Classification, Function approximation, Learning algorithms, Neural networks, Second-order systems",

author = "Noriyasu Homma and Gupta, {Madan M.}",

year = "2002",

language = "English",

isbn = "1889335185",

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

pages = "177--182",

booktitle = "Multimedia, Image Processing and Soft Computing",

note = "4th 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 ; Conference date: 09-06-2002 Through 13-06-2002",

}

Homma, N & Gupta, MM 2002, Study on general Second-Order Neural Units (SONUs). in Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002. Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002, vol. 13, pp. 177-182, 4th 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, 02/6/9.

Study on general Second-Order Neural Units (SONUs). / Homma, Noriyasu; Gupta, Madan M.
Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002. 2002. p. 177-182 (Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002; Vol. 13).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Study on general Second-Order Neural Units (SONUs)

AU - Homma, Noriyasu

AU - Gupta, Madan M.

PY - 2002

Y1 - 2002

N2 - 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.

AB - 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.

KW - Classification

KW - Function approximation

KW - Learning algorithms

KW - Neural networks

KW - Second-order systems

UR - http://www.scopus.com/inward/record.url?scp=78650056373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650056373&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78650056373

SN - 1889335185

SN - 9781889335186

T3 - Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002

SP - 177

EP - 182

BT - Multimedia, Image Processing and Soft Computing

T2 - 4th 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

Y2 - 9 June 2002 through 13 June 2002

ER -

Homma N, Gupta MM. Study on general Second-Order Neural Units (SONUs). In Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002. 2002. p. 177-182. (Multimedia, Image Processing and Soft Computing: Trends, Principles and Applications - Proceedings of the 5th Biannual World Automation Congress, WAC 2002, ISSCI 2002 and IFMIP 2002).

Study on general Second-Order Neural Units (SONUs)

Abstract

Publication series

Conference

Keywords

Other files and links

Fingerprint

Cite this