四元数值神经网络的Levenberg-Marquardt学习算法

2016 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC) Pub Date : 2016-09-01 DOI:10.1109/SYNASC.2016.050

Călin-Adrian Popa

{"title":"四元数值神经网络的Levenberg-Marquardt学习算法","authors":"Călin-Adrian Popa","doi":"10.1109/SYNASC.2016.050","DOIUrl":null,"url":null,"abstract":"In this paper, we present the deduction of the Levenberg-Marquardt algorithm for training quaternion-valued feedforward neural networks, using the framework of the HR calculus. Its performances in the real-and complex-valued cases lead to the idea of extending it to the quaternion domain, also. The proposed method is exemplified on time series prediction applications, showing a significant improvement over the quaternion gradient descent algorithm.","PeriodicalId":268635,"journal":{"name":"2016 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","volume":"75 2-3","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Levenberg-Marquardt Learning Algorithm for Quaternion-Valued Neural Networks\",\"authors\":\"Călin-Adrian Popa\",\"doi\":\"10.1109/SYNASC.2016.050\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we present the deduction of the Levenberg-Marquardt algorithm for training quaternion-valued feedforward neural networks, using the framework of the HR calculus. Its performances in the real-and complex-valued cases lead to the idea of extending it to the quaternion domain, also. The proposed method is exemplified on time series prediction applications, showing a significant improvement over the quaternion gradient descent algorithm.\",\"PeriodicalId\":268635,\"journal\":{\"name\":\"2016 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)\",\"volume\":\"75 2-3\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SYNASC.2016.050\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SYNASC.2016.050","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

在本文中，我们提出了Levenberg-Marquardt算法的推导，用于训练四元数值前馈神经网络，使用HR微积分的框架。它在实值和复值情况下的性能也使其扩展到四元数域的想法。该方法在时间序列预测中的应用表明，该方法比四元数梯度下降算法有明显的改进。

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

Levenberg-Marquardt Learning Algorithm for Quaternion-Valued Neural Networks

In this paper, we present the deduction of the Levenberg-Marquardt algorithm for training quaternion-valued feedforward neural networks, using the framework of the HR calculus. Its performances in the real-and complex-valued cases lead to the idea of extending it to the quaternion domain, also. The proposed method is exemplified on time series prediction applications, showing a significant improvement over the quaternion gradient descent algorithm.

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

2016 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)

自引率

0.00%

发文量