基于四元数的神经网络研究

Proceedings of the 41st SICE Annual Conference. SICE 2002. Pub Date : 2002-08-05 DOI:10.1109/SICE.2002.1195247

T. Kusakabe, T. Isokawa, N. Kouda, N. Matsui

{"title":"基于四元数的神经网络研究","authors":"T. Kusakabe, T. Isokawa, N. Kouda, N. Matsui","doi":"10.1109/SICE.2002.1195247","DOIUrl":null,"url":null,"abstract":"A quaternion neural network with nonlinear function is presented in this paper. The quaternion neuron adopts geometrical transformations as operators of data to be processed. Back Propagation for the layered network: with quaternion neurons is also formulated. The simulation results show that the presented model has the ability in learning affine transformation of 3D figures. while conventional neural network can hardly acquire.","PeriodicalId":301855,"journal":{"name":"Proceedings of the 41st SICE Annual Conference. SICE 2002.","volume":"13 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2002-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"A study of neural network based on quaternion\",\"authors\":\"T. Kusakabe, T. Isokawa, N. Kouda, N. Matsui\",\"doi\":\"10.1109/SICE.2002.1195247\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A quaternion neural network with nonlinear function is presented in this paper. The quaternion neuron adopts geometrical transformations as operators of data to be processed. Back Propagation for the layered network: with quaternion neurons is also formulated. The simulation results show that the presented model has the ability in learning affine transformation of 3D figures. while conventional neural network can hardly acquire.\",\"PeriodicalId\":301855,\"journal\":{\"name\":\"Proceedings of the 41st SICE Annual Conference. SICE 2002.\",\"volume\":\"13 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2002-08-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 41st SICE Annual Conference. SICE 2002.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SICE.2002.1195247\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 41st SICE Annual Conference. SICE 2002.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SICE.2002.1195247","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 4

摘要

提出了一种非线性函数四元数神经网络。四元数神经元采用几何变换作为待处理数据的运算符。反向传播的分层网络:与四元数神经元也制定。仿真结果表明，该模型具有学习三维图形仿射变换的能力。而传统神经网络难以获取。

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

A study of neural network based on quaternion

A quaternion neural network with nonlinear function is presented in this paper. The quaternion neuron adopts geometrical transformations as operators of data to be processed. Back Propagation for the layered network: with quaternion neurons is also formulated. The simulation results show that the presented model has the ability in learning affine transformation of 3D figures. while conventional neural network can hardly acquire.

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

Proceedings of the 41st SICE Annual Conference. SICE 2002.

自引率

0.00%

发文量