文件列表:

ART网络C++\ART.CPP (10209, 1995-08-27)
ART网络C++\ART.EXE (47888, 1995-08-27)
ART网络C++\ART001.DAT (236, 1994-12-27)
ART网络C++\ART001.OUT (3170, 1995-08-27)
ART网络C++\ART002.DAT (236, 1994-12-27)
ART网络C++\ART002.OUT (3846, 1995-08-27)
ART网络C++ (0, 2008-03-30)

这程序是《神经网络模式识别及其实现》（Pattern Recognition with Neural Networks in C++)美Abhijit S. Pandya等著电子工业出版社1999年6月 书号ISBN 7-5053-5088-9 This directory contains code implementing the adaptive resonance theory (ART) network. Source code may be found in ART.CPP. Sample training data is found in ART001.DAT and ART002.DAT. Sample results are found in ART001.OUT and ART002.OUT. The ART program accepts input consisting of vectors and calculates the ART networks top down and bottom up weights. Output is directed to the screen. Usage for ART is: ART PATTERN_FILE_NAME Specification of a test file is optional. The format of both the pattern file is: NumPatterns - Number of patterns (int) SizeVector - Size of vector (int) VigilThresh - Vigilence threshold (real) vect[1,1] ... vect[1,SizeVect] - pattern vector 1 (int) vect[2,1] ... vect[2,SizeVect] - pattern vector 2 (int) . . . . . . vect[NPat,1] ... vect[NClust,SizeVector] - pattern vector N (int) To compile: ICC ART.CPP 

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：