基于改进感知器的机器人学习推理网络

International Conference on Information Acquisition, 2004. Proceedings. Pub Date : 2004-06-21 DOI:10.1109/ICIA.2004.1373375

Yibin Song, Peijin Wang, Limin Sun

{"title":"基于改进感知器的机器人学习推理网络","authors":"Yibin Song, Peijin Wang, Limin Sun","doi":"10.1109/ICIA.2004.1373375","DOIUrl":null,"url":null,"abstract":"Based on the principle of multilayer perceptron (MLP), we present a new algorithm with adaptive learning rate factors for the improvement of MLP learning. The improved algorithm is applied to the learning of an illative network for the escaping process of robot. The simulations show the improved algorithm has good effects on speeding up learning process and bettering its learning convergence and robust performance.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"41 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An illative network for robot learning based on the improved perceptron\",\"authors\":\"Yibin Song, Peijin Wang, Limin Sun\",\"doi\":\"10.1109/ICIA.2004.1373375\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Based on the principle of multilayer perceptron (MLP), we present a new algorithm with adaptive learning rate factors for the improvement of MLP learning. The improved algorithm is applied to the learning of an illative network for the escaping process of robot. The simulations show the improved algorithm has good effects on speeding up learning process and bettering its learning convergence and robust performance.\",\"PeriodicalId\":297178,\"journal\":{\"name\":\"International Conference on Information Acquisition, 2004. Proceedings.\",\"volume\":\"41 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2004-06-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Conference on Information Acquisition, 2004. Proceedings.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICIA.2004.1373375\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Information Acquisition, 2004. Proceedings.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIA.2004.1373375","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

基于多层感知器(MLP)的原理，提出了一种具有自适应学习率因子的多层感知器学习算法。将改进后的算法应用于机器人逃跑过程的模拟网络学习。仿真结果表明，改进后的算法在加快学习过程、提高学习收敛性和鲁棒性方面具有良好的效果。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

An illative network for robot learning based on the improved perceptron

Based on the principle of multilayer perceptron (MLP), we present a new algorithm with adaptive learning rate factors for the improvement of MLP learning. The improved algorithm is applied to the learning of an illative network for the escaping process of robot. The simulations show the improved algorithm has good effects on speeding up learning process and bettering its learning convergence and robust performance.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

International Conference on Information Acquisition, 2004. Proceedings.

自引率

0.00%

发文量