白日做梦的Hopfield网络及其对相关数据的惊人有效性

IF 6.3 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Neural Networks Pub Date : 2025-06-01 Epub Date: 2025-02-13 DOI:10.1016/j.neunet.2025.107216
Ludovica Serricchio , Dario Bocchi , Claudio Chilin , Raffaele Marino , Matteo Negri , Chiara Cammarota , Federico Ricci-Tersenghi
{"title":"白日做梦的Hopfield网络及其对相关数据的惊人有效性","authors":"Ludovica Serricchio ,&nbsp;Dario Bocchi ,&nbsp;Claudio Chilin ,&nbsp;Raffaele Marino ,&nbsp;Matteo Negri ,&nbsp;Chiara Cammarota ,&nbsp;Federico Ricci-Tersenghi","doi":"10.1016/j.neunet.2025.107216","DOIUrl":null,"url":null,"abstract":"<div><div>To improve the storage capacity of the Hopfield model, we develop a version of the dreaming algorithm that <em>perpetually</em> reinforces the patterns to be stored (as in the Hebb rule), and erases the spurious memories (as in dreaming algorithms). For this reason, we called it <em>Daydreaming</em>. Daydreaming is not destructive and it converges asymptotically to stationary retrieval maps. When trained on random uncorrelated examples, the model shows optimal performance in terms of the size of the basins of attraction of stored examples and the quality of reconstruction. We also train the Daydreaming algorithm on correlated data obtained via the random-features model and argue that it spontaneously exploits the correlations thus increasing even further the storage capacity and the size of the basins of attraction. Moreover, the Daydreaming algorithm is also able to stabilize the features hidden in the data. Finally, we test Daydreaming on the MNIST dataset and show that it still works surprisingly well, producing attractors that are close to unseen examples and class prototypes.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"186 ","pages":"Article 107216"},"PeriodicalIF":6.3000,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Daydreaming Hopfield Networks and their surprising effectiveness on correlated data\",\"authors\":\"Ludovica Serricchio ,&nbsp;Dario Bocchi ,&nbsp;Claudio Chilin ,&nbsp;Raffaele Marino ,&nbsp;Matteo Negri ,&nbsp;Chiara Cammarota ,&nbsp;Federico Ricci-Tersenghi\",\"doi\":\"10.1016/j.neunet.2025.107216\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>To improve the storage capacity of the Hopfield model, we develop a version of the dreaming algorithm that <em>perpetually</em> reinforces the patterns to be stored (as in the Hebb rule), and erases the spurious memories (as in dreaming algorithms). For this reason, we called it <em>Daydreaming</em>. Daydreaming is not destructive and it converges asymptotically to stationary retrieval maps. When trained on random uncorrelated examples, the model shows optimal performance in terms of the size of the basins of attraction of stored examples and the quality of reconstruction. We also train the Daydreaming algorithm on correlated data obtained via the random-features model and argue that it spontaneously exploits the correlations thus increasing even further the storage capacity and the size of the basins of attraction. Moreover, the Daydreaming algorithm is also able to stabilize the features hidden in the data. Finally, we test Daydreaming on the MNIST dataset and show that it still works surprisingly well, producing attractors that are close to unseen examples and class prototypes.</div></div>\",\"PeriodicalId\":49763,\"journal\":{\"name\":\"Neural Networks\",\"volume\":\"186 \",\"pages\":\"Article 107216\"},\"PeriodicalIF\":6.3000,\"publicationDate\":\"2025-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Neural Networks\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0893608025000954\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/2/13 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neural Networks","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0893608025000954","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/2/13 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

为了提高Hopfield模型的存储容量,我们开发了一个做梦算法的版本,它可以永久地强化要存储的模式(如Hebb规则),并消除虚假记忆(如做梦算法)。出于这个原因,我们称之为白日梦。白日梦是不具有破坏性的,它渐近收敛于平稳检索地图。当在随机不相关的样本上训练时,该模型在存储样本的吸引力盆地的大小和重建质量方面表现出最佳性能。我们还在通过随机特征模型获得的相关数据上训练Daydreaming算法,并认为它会自发地利用相关性,从而进一步增加存储容量和吸引力盆地的大小。此外,Daydreaming算法还可以稳定隐藏在数据中的特征。最后,我们在MNIST数据集上测试了Daydreaming,并表明它仍然出奇地好,产生的吸引子接近于未见过的示例和类原型。
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
Daydreaming Hopfield Networks and their surprising effectiveness on correlated data
To improve the storage capacity of the Hopfield model, we develop a version of the dreaming algorithm that perpetually reinforces the patterns to be stored (as in the Hebb rule), and erases the spurious memories (as in dreaming algorithms). For this reason, we called it Daydreaming. Daydreaming is not destructive and it converges asymptotically to stationary retrieval maps. When trained on random uncorrelated examples, the model shows optimal performance in terms of the size of the basins of attraction of stored examples and the quality of reconstruction. We also train the Daydreaming algorithm on correlated data obtained via the random-features model and argue that it spontaneously exploits the correlations thus increasing even further the storage capacity and the size of the basins of attraction. Moreover, the Daydreaming algorithm is also able to stabilize the features hidden in the data. Finally, we test Daydreaming on the MNIST dataset and show that it still works surprisingly well, producing attractors that are close to unseen examples and class prototypes.
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
Neural Networks
Neural Networks 工程技术-计算机:人工智能
CiteScore
13.90
自引率
7.70%
发文量
425
审稿时长
67 days
期刊介绍: Neural Networks is a platform that aims to foster an international community of scholars and practitioners interested in neural networks, deep learning, and other approaches to artificial intelligence and machine learning. Our journal invites submissions covering various aspects of neural networks research, from computational neuroscience and cognitive modeling to mathematical analyses and engineering applications. By providing a forum for interdisciplinary discussions between biology and technology, we aim to encourage the development of biologically-inspired artificial intelligence.
期刊最新文献
Multi-neurotransmitter synergistically regulated basal ganglia reinforcement learning model HC-GLAD: Dual hyperbolic contrastive learning for unsupervised graph-level anomaly detection Revisiting deep information propagation: Fractal frontier and finite-size effects Topology structure optimization of reservoirs using GLMY homology A text-guided cross-hierarchical fusion and multi-task learning framework for multimodal sentiment analysis
×
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学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
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