Development of quadratic neural unit with applications to pattern classification

S. Redlapalli, M. M. Gupta*, K. Y. Song

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

12 引用 (Scopus)

摘要

The computational neural-network structures described in the literature are often based on the concept of linear neural units (LNUs). The biological neuron is a complex computing element, which performs more computations than just linear summation. The computational efficiency of the neural network depends on its structure and the training methods employed. Higher-order combinations of inputs and weights will yield higher neural performance. Here, a quadratic-neural unit (QNU) has been developed using a novel general matrix form of the quadratic operation. We have used the QNU for realizing different logic circuits.

源语言英语
主期刊名4th International Symposium on Uncertainty Modeling and Analysis, ISUMA 2003
编辑Nii O. Attoh-Okine, Bilal M. Ayyub
出版商Institute of Electrical and Electronics Engineers Inc.
141-146
页数6
ISBN(电子版)0769519970, 9780769519975
DOI
出版状态已出版 - 2003
已对外发布
活动4th International Symposium on Uncertainty Modeling and Analysis, ISUMA 2003 - College Park, 美国
期限: 21 9月 200324 9月 2003

出版系列

姓名4th International Symposium on Uncertainty Modeling and Analysis, ISUMA 2003

会议

会议4th International Symposium on Uncertainty Modeling and Analysis, ISUMA 2003
国家/地区美国
College Park
时期21/09/0324/09/03

指纹

探究 'Development of quadratic neural unit with applications to pattern classification' 的科研主题。它们共同构成独一无二的指纹。

引用此