{"title":"神经元同伦回归量","authors":"R. Rodrigo, D. Patiño, G. Schweickardt","doi":"10.1109/RPIC53795.2021.9648481","DOIUrl":null,"url":null,"abstract":"In this work, a neural model is proposed, which solves two limitations of artificial neural networks. The first refers to the ability to extrapolate outside the domain of the training data. The second arises when only a small sample is available for training. On the other hand, there is a need to characterize a complex system, and the dynamics of its components is partially known. The proposed model is based on the construction of a regressor from a feasible space, using Homotopy Analysis. In this way, a functional neural network is obtained.","PeriodicalId":299649,"journal":{"name":"2021 XIX Workshop on Information Processing and Control (RPIC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Neuronal Homotopy Regressors\",\"authors\":\"R. Rodrigo, D. Patiño, G. Schweickardt\",\"doi\":\"10.1109/RPIC53795.2021.9648481\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this work, a neural model is proposed, which solves two limitations of artificial neural networks. The first refers to the ability to extrapolate outside the domain of the training data. The second arises when only a small sample is available for training. On the other hand, there is a need to characterize a complex system, and the dynamics of its components is partially known. The proposed model is based on the construction of a regressor from a feasible space, using Homotopy Analysis. In this way, a functional neural network is obtained.\",\"PeriodicalId\":299649,\"journal\":{\"name\":\"2021 XIX Workshop on Information Processing and Control (RPIC)\",\"volume\":\"23 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-11-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 XIX Workshop on Information Processing and Control (RPIC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/RPIC53795.2021.9648481\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 XIX Workshop on Information Processing and Control (RPIC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/RPIC53795.2021.9648481","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
In this work, a neural model is proposed, which solves two limitations of artificial neural networks. The first refers to the ability to extrapolate outside the domain of the training data. The second arises when only a small sample is available for training. On the other hand, there is a need to characterize a complex system, and the dynamics of its components is partially known. The proposed model is based on the construction of a regressor from a feasible space, using Homotopy Analysis. In this way, a functional neural network is obtained.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
