广义全息还原表征

Calvin Yeung, Zhuowen Zou, Mohsen Imani
{"title":"广义全息还原表征","authors":"Calvin Yeung, Zhuowen Zou, Mohsen Imani","doi":"arxiv-2405.09689","DOIUrl":null,"url":null,"abstract":"Deep learning has achieved remarkable success in recent years. Central to its\nsuccess is its ability to learn representations that preserve task-relevant\nstructure. However, massive energy, compute, and data costs are required to\nlearn general representations. This paper explores Hyperdimensional Computing\n(HDC), a computationally and data-efficient brain-inspired alternative. HDC\nacts as a bridge between connectionist and symbolic approaches to artificial\nintelligence (AI), allowing explicit specification of representational\nstructure as in symbolic approaches while retaining the flexibility of\nconnectionist approaches. However, HDC's simplicity poses challenges for\nencoding complex compositional structures, especially in its binding operation.\nTo address this, we propose Generalized Holographic Reduced Representations\n(GHRR), an extension of Fourier Holographic Reduced Representations (FHRR), a\nspecific HDC implementation. GHRR introduces a flexible, non-commutative\nbinding operation, enabling improved encoding of complex data structures while\npreserving HDC's desirable properties of robustness and transparency. In this\nwork, we introduce the GHRR framework, prove its theoretical properties and its\nadherence to HDC properties, explore its kernel and binding characteristics,\nand perform empirical experiments showcasing its flexible non-commutativity,\nenhanced decoding accuracy for compositional structures, and improved\nmemorization capacity compared to FHRR.","PeriodicalId":501033,"journal":{"name":"arXiv - CS - Symbolic Computation","volume":"12 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Generalized Holographic Reduced Representations\",\"authors\":\"Calvin Yeung, Zhuowen Zou, Mohsen Imani\",\"doi\":\"arxiv-2405.09689\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Deep learning has achieved remarkable success in recent years. Central to its\\nsuccess is its ability to learn representations that preserve task-relevant\\nstructure. However, massive energy, compute, and data costs are required to\\nlearn general representations. This paper explores Hyperdimensional Computing\\n(HDC), a computationally and data-efficient brain-inspired alternative. HDC\\nacts as a bridge between connectionist and symbolic approaches to artificial\\nintelligence (AI), allowing explicit specification of representational\\nstructure as in symbolic approaches while retaining the flexibility of\\nconnectionist approaches. However, HDC's simplicity poses challenges for\\nencoding complex compositional structures, especially in its binding operation.\\nTo address this, we propose Generalized Holographic Reduced Representations\\n(GHRR), an extension of Fourier Holographic Reduced Representations (FHRR), a\\nspecific HDC implementation. GHRR introduces a flexible, non-commutative\\nbinding operation, enabling improved encoding of complex data structures while\\npreserving HDC's desirable properties of robustness and transparency. In this\\nwork, we introduce the GHRR framework, prove its theoretical properties and its\\nadherence to HDC properties, explore its kernel and binding characteristics,\\nand perform empirical experiments showcasing its flexible non-commutativity,\\nenhanced decoding accuracy for compositional structures, and improved\\nmemorization capacity compared to FHRR.\",\"PeriodicalId\":501033,\"journal\":{\"name\":\"arXiv - CS - Symbolic Computation\",\"volume\":\"12 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-05-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Symbolic Computation\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2405.09689\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Symbolic Computation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2405.09689","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

深度学习近年来取得了令人瞩目的成就。其成功的核心在于它能够学习保留任务相关结构的表征。然而,学习一般表征需要大量的能源、计算和数据成本。本文探讨了超维计算(HDC),这是一种计算和数据高效的大脑启发式替代方案。HDC 是连接主义和符号方法之间的一座桥梁,它允许像符号方法那样明确指定表征结构,同时保留连接主义方法的灵活性。为了解决这个问题,我们提出了广义全息还原表征(GHRR),它是傅立叶全息还原表征(FHRR)的扩展,是 HDC 的具体实现。GHRR 引入了灵活的非交换绑定操作,在保留 HDC 理想的鲁棒性和透明性的同时,改进了复杂数据结构的编码。在这项工作中,我们介绍了 GHRR 框架,证明了它的理论特性及其与 HDC 特性的一致性,探索了它的内核和绑定特性,并进行了实证实验,展示了它灵活的非交换性,与 FHRR 相比,它提高了组成结构的解码精度,并改善了记忆能力。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Generalized Holographic Reduced Representations
Deep learning has achieved remarkable success in recent years. Central to its success is its ability to learn representations that preserve task-relevant structure. However, massive energy, compute, and data costs are required to learn general representations. This paper explores Hyperdimensional Computing (HDC), a computationally and data-efficient brain-inspired alternative. HDC acts as a bridge between connectionist and symbolic approaches to artificial intelligence (AI), allowing explicit specification of representational structure as in symbolic approaches while retaining the flexibility of connectionist approaches. However, HDC's simplicity poses challenges for encoding complex compositional structures, especially in its binding operation. To address this, we propose Generalized Holographic Reduced Representations (GHRR), an extension of Fourier Holographic Reduced Representations (FHRR), a specific HDC implementation. GHRR introduces a flexible, non-commutative binding operation, enabling improved encoding of complex data structures while preserving HDC's desirable properties of robustness and transparency. In this work, we introduce the GHRR framework, prove its theoretical properties and its adherence to HDC properties, explore its kernel and binding characteristics, and perform empirical experiments showcasing its flexible non-commutativity, enhanced decoding accuracy for compositional structures, and improved memorization capacity compared to FHRR.
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
自引率
0.00%
发文量
0
期刊最新文献
Synthesizing Evolving Symbolic Representations for Autonomous Systems Introducing Quantification into a Hierarchical Graph Rewriting Language Towards Verified Polynomial Factorisation Symbolic Regression with a Learned Concept Library Active Symbolic Discovery of Ordinary Differential Equations via Phase Portrait Sketching
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1