通过内部高维混沌活动生成模型

Samantha J. Fournier, Pierfrancesco Urbani
{"title":"通过内部高维混沌活动生成模型","authors":"Samantha J. Fournier, Pierfrancesco Urbani","doi":"arxiv-2405.10822","DOIUrl":null,"url":null,"abstract":"Generative modeling aims at producing new datapoints whose statistical\nproperties resemble the ones in a training dataset. In recent years, there has\nbeen a burst of machine learning techniques and settings that can achieve this\ngoal with remarkable performances. In most of these settings, one uses the\ntraining dataset in conjunction with noise, which is added as a source of\nstatistical variability and is essential for the generative task. Here, we\nexplore the idea of using internal chaotic dynamics in high-dimensional chaotic\nsystems as a way to generate new datapoints from a training dataset. We show\nthat simple learning rules can achieve this goal within a set of vanilla\narchitectures and characterize the quality of the generated datapoints through\nstandard accuracy measures.","PeriodicalId":501066,"journal":{"name":"arXiv - PHYS - Disordered Systems and Neural Networks","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Generative modeling through internal high-dimensional chaotic activity\",\"authors\":\"Samantha J. Fournier, Pierfrancesco Urbani\",\"doi\":\"arxiv-2405.10822\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Generative modeling aims at producing new datapoints whose statistical\\nproperties resemble the ones in a training dataset. In recent years, there has\\nbeen a burst of machine learning techniques and settings that can achieve this\\ngoal with remarkable performances. In most of these settings, one uses the\\ntraining dataset in conjunction with noise, which is added as a source of\\nstatistical variability and is essential for the generative task. Here, we\\nexplore the idea of using internal chaotic dynamics in high-dimensional chaotic\\nsystems as a way to generate new datapoints from a training dataset. We show\\nthat simple learning rules can achieve this goal within a set of vanilla\\narchitectures and characterize the quality of the generated datapoints through\\nstandard accuracy measures.\",\"PeriodicalId\":501066,\"journal\":{\"name\":\"arXiv - PHYS - Disordered Systems and Neural Networks\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-05-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Disordered Systems and Neural Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2405.10822\",\"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 - PHYS - Disordered Systems and Neural Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2405.10822","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

生成模型旨在生成统计属性与训练数据集相似的新数据点。近年来,机器学习技术和设置层出不穷,这些技术和设置都能以出色的性能实现这一目标。在大多数情况下,人们会将训练数据集与噪声结合起来使用,而噪声是作为统计变异性的来源添加的,对于生成任务至关重要。在这里,我们探讨了在高维混沌系统中使用内部混沌动力学作为从训练数据集生成新数据点的方法。我们展示了简单的学习规则就能在一套虚构架构中实现这一目标,并通过标准的准确度测量来表征生成数据点的质量。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Generative modeling through internal high-dimensional chaotic activity
Generative modeling aims at producing new datapoints whose statistical properties resemble the ones in a training dataset. In recent years, there has been a burst of machine learning techniques and settings that can achieve this goal with remarkable performances. In most of these settings, one uses the training dataset in conjunction with noise, which is added as a source of statistical variability and is essential for the generative task. Here, we explore the idea of using internal chaotic dynamics in high-dimensional chaotic systems as a way to generate new datapoints from a training dataset. We show that simple learning rules can achieve this goal within a set of vanilla architectures and characterize the quality of the generated datapoints through standard accuracy measures.
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
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信