{"title":"超立方体上的神经网络模式识别","authors":"W. Furmanski","doi":"10.1145/63047.63055","DOIUrl":null,"url":null,"abstract":"The objective of this work is to study the performance characteristics of the back-propagation model for pattern recognition. Specifically, the test case of recognition of Chinese characters is studied on an ELXSI-6400 and MARK III hypercube. Preliminary results indicate that local spatial decomposition of characters in the training set leads to simple parallel implementation of the neural net model on hypercubes, and also serves as an effective pre-processor which provides high quality of recognition and good efficiency.","PeriodicalId":299435,"journal":{"name":"Conference on Hypercube Concurrent Computers and Applications","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1989-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"Pattern recognition by neural network model on hypercubes\",\"authors\":\"W. Furmanski\",\"doi\":\"10.1145/63047.63055\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The objective of this work is to study the performance characteristics of the back-propagation model for pattern recognition. Specifically, the test case of recognition of Chinese characters is studied on an ELXSI-6400 and MARK III hypercube. Preliminary results indicate that local spatial decomposition of characters in the training set leads to simple parallel implementation of the neural net model on hypercubes, and also serves as an effective pre-processor which provides high quality of recognition and good efficiency.\",\"PeriodicalId\":299435,\"journal\":{\"name\":\"Conference on Hypercube Concurrent Computers and Applications\",\"volume\":\"12 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1989-01-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Conference on Hypercube Concurrent Computers and Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/63047.63055\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Conference on Hypercube Concurrent Computers and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/63047.63055","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Pattern recognition by neural network model on hypercubes
The objective of this work is to study the performance characteristics of the back-propagation model for pattern recognition. Specifically, the test case of recognition of Chinese characters is studied on an ELXSI-6400 and MARK III hypercube. Preliminary results indicate that local spatial decomposition of characters in the training set leads to simple parallel implementation of the neural net model on hypercubes, and also serves as an effective pre-processor which provides high quality of recognition and good efficiency.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
