Introduction to the theory and applications of neural networks with quadratic junctions

Nicholas DeClaris, Mu Chun Su

研究成果: 書貢獻/報告類型會議論文篇章同行評審

7 引文 斯高帕斯(Scopus)

摘要

This paper provides a statistical viewpoint for understanding and using a novel class of neural networks that contain quadratic junctions. It is shown that any Gaussian classifier can be mapped into a quadratic neuron. When the data clusters by means of hyperellipsoids the quadratic neurons provide significant advantages over other representation schemes. Moreover there are cases that even when the data are non-Gaussian, the multilayer neural networks composed of quadratic neurons provide efficient solutions to these pattern recognition problems.

原文???core.languages.en_GB???
主出版物標題1992 IEEE International Conference on Systems, Man, and Cybernetics
主出版物子標題Emergent Innovations in Information Transfer Processing and Decision Making, SMC 1992
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1320-1325
頁數6
ISBN(電子)0780307208, 9780780307209
DOIs
出版狀態已出版 - 1992
事件IEEE International Conference on Systems, Man, and Cybernetics, SMC 1992 - Chicago, United States
持續時間: 18 10月 199221 10月 1992

出版系列

名字Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
1992-January
ISSN(列印)1062-922X

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???IEEE International Conference on Systems, Man, and Cybernetics, SMC 1992
國家/地區United States
城市Chicago
期間18/10/9221/10/92

指紋

深入研究「Introduction to the theory and applications of neural networks with quadratic junctions」主題。共同形成了獨特的指紋。

引用此