A Novel Rough Neural Network and Its Training Algorithm
スポンサーリンク
概要
- 論文の詳細を見る
A novel rough neural network (RNN) structure and its application are proposed in this paper. We principally introduce its architecture and training algorithms: the genetic training algorithm (GA) and the tabu search training algorithm (TSA). We first compare RNN with the conventional NN trained by the BP algorithm in two-dimensional data classification. Then we compare RNN with NN by the same training algorithm (TSA) in functional approximation. Experiment results show that the proposed RNN is more effective than NN, not only in computation time hut also in performance.
- 社団法人電子情報通信学会の論文
- 2002-02-01
著者
-
SUN Sheng-He
Department of Automatic Test and Control, Harbin Institute of Technology
-
Zhang Zhao-li
Department Of Automatic Test And Control Harbin Institute Of Technology
-
MEI Xiao-Dan
Department of Automatic Test and Control, Harbin Institute of Technology
-
Mei Xiao-dan
Department Of Automatic Test And Control Harbin Institute Of Technology
-
Sun Sheng-he
Department Of Automatic Test And Control Harbin Institute Of Technology
関連論文
- Image Coding Based on Classified Side-Match Vector Quantization
- Fast K Nearest Neighbors Search Algorithm Based on Wavelet Transform(Vision)
- Equal-Average Equal-Variance Equal-Norm Nearest Neighbor Search Algorithm for Vector Quantization
- Digital Image Watermarking Method Based on Vector Quantization with Labeled Codewords(Applications of Information Security Technipues)
- A Multipurpose Image Watermarking Method for Copyright Notification and Protection(Applications of Information Security Techniques)
- Fast Codeword Search Algorithm for Image Vector Quantization Based on Ordered Hadamard Transform(Image Processing, Image Pattern Recognition)
- A Novel Rough Neural Network and Its Training Algorithm
- A Fast K Nearest Neighbors Classification Algorithm(Image)