找回密碼
 To register

QQ登錄

只需一步,快速開始

掃一掃,訪問微社區(qū)

打印 上一主題 下一主題

Titlebook: Geometric Structures of Statistical Physics, Information Geometry, and Learning; SPIGL‘20, Les Houche Frédéric Barbaresco,Frank Nielsen Con

[復(fù)制鏈接]
查看: 14352|回復(fù): 54
樓主
發(fā)表于 2025-3-21 18:15:18 | 只看該作者 |倒序?yàn)g覽 |閱讀模式
書目名稱Geometric Structures of Statistical Physics, Information Geometry, and Learning
副標(biāo)題SPIGL‘20, Les Houche
編輯Frédéric Barbaresco,Frank Nielsen
視頻videohttp://file.papertrans.cn/384/383614/383614.mp4
概述Provides new geometric foundations of inference in machine learning based on statistical physics.Deepens mathematical physics models with new insights from statistical machine learning.Combines numeri
叢書名稱Springer Proceedings in Mathematics & Statistics
圖書封面Titlebook: Geometric Structures of Statistical Physics, Information Geometry, and Learning; SPIGL‘20, Les Houche Frédéric Barbaresco,Frank Nielsen Con
描述.Machine learning and artificial intelligence increasingly use methodological tools rooted in statistical physics. Conversely, limitations and pitfalls encountered in AI question the very foundations of statistical physics. This interplay between AI and statistical physics has been attested since the birth of AI, and principles underpinning statistical physics can shed new light on the conceptual basis of AI. During the last fifty years, statistical physics has been investigated through new geometric structures allowing covariant formalization of the thermodynamics. Inference methods in machine learning have begun to adapt these new geometric structures to process data in more abstract representation spaces..This volume collects selected contributions on the interplay of statistical physics and artificial intelligence. The aim is to provide a constructive dialogue around a common foundation to allow the establishment of new principles and laws governing these two disciplines in a unified manner. The contributions were presented at the workshop on the Joint Structures and Common Foundation of Statistical Physics, Information Geometry and Inference for Learning which was held in Les
出版日期Conference proceedings 2021
關(guān)鍵詞Conference Proceedings; Statistical inference; Geometric mechanics; Lie group machine learning; Informat
版次1
doihttps://doi.org/10.1007/978-3-030-77957-3
isbn_softcover978-3-030-77959-7
isbn_ebook978-3-030-77957-3Series ISSN 2194-1009 Series E-ISSN 2194-1017
issn_series 2194-1009
copyrightThe Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerl
The information of publication is updating

書目名稱Geometric Structures of Statistical Physics, Information Geometry, and Learning影響因子(影響力)




書目名稱Geometric Structures of Statistical Physics, Information Geometry, and Learning影響因子(影響力)學(xué)科排名




書目名稱Geometric Structures of Statistical Physics, Information Geometry, and Learning網(wǎng)絡(luò)公開度




書目名稱Geometric Structures of Statistical Physics, Information Geometry, and Learning網(wǎng)絡(luò)公開度學(xué)科排名




書目名稱Geometric Structures of Statistical Physics, Information Geometry, and Learning被引頻次




書目名稱Geometric Structures of Statistical Physics, Information Geometry, and Learning被引頻次學(xué)科排名




書目名稱Geometric Structures of Statistical Physics, Information Geometry, and Learning年度引用




書目名稱Geometric Structures of Statistical Physics, Information Geometry, and Learning年度引用學(xué)科排名




書目名稱Geometric Structures of Statistical Physics, Information Geometry, and Learning讀者反饋




書目名稱Geometric Structures of Statistical Physics, Information Geometry, and Learning讀者反饋學(xué)科排名




單選投票, 共有 1 人參與投票
 

0票 0.00%

Perfect with Aesthetics

 

0票 0.00%

Better Implies Difficulty

 

1票 100.00%

Good and Satisfactory

 

0票 0.00%

Adverse Performance

 

0票 0.00%

Disdainful Garbage

您所在的用戶組沒有投票權(quán)限
沙發(fā)
發(fā)表于 2025-3-21 21:49:19 | 只看該作者
板凳
發(fā)表于 2025-3-22 01:24:30 | 只看該作者
Sequelae of Ebola Virus Disease, by briefly reviewing the different approaches to build densities on a manifold and shows the interest of wrapped distributions. We then construct wrapped densities on .(.) and discuss their statistical estimation. We conclude by an opening to the case of symmetric spaces.
地板
發(fā)表于 2025-3-22 08:14:05 | 只看該作者
https://doi.org/10.1007/978-94-015-5853-2nsion space. The entropy is generalized as a 4-vector and the temperature as a 5-vector. The introduction of the friction and momentum tensors allows to obtain a covariant formulation of the first and second principles of Thermodynamics.
5#
發(fā)表于 2025-3-22 11:32:40 | 只看該作者
6#
發(fā)表于 2025-3-22 14:04:42 | 只看該作者
7#
發(fā)表于 2025-3-22 18:52:58 | 只看該作者
8#
發(fā)表于 2025-3-23 00:58:19 | 只看該作者
Galilean Thermodynamics of Continuansion space. The entropy is generalized as a 4-vector and the temperature as a 5-vector. The introduction of the friction and momentum tensors allows to obtain a covariant formulation of the first and second principles of Thermodynamics.
9#
發(fā)表于 2025-3-23 05:14:29 | 只看該作者
Nonparametric Estimations and the Diffeological Fisher Metricnd slightly extending Lê’s theory in [.] to include weakly .-diffeological statistical models. Then we introduce the resulting notions of the diffeological Fisher distance, the diffeological Hausdorff–Jeffrey measure and explain their role in classical and Bayesian nonparametric estimation problems in statistics.
10#
發(fā)表于 2025-3-23 09:37:40 | 只看該作者
 關(guān)于派博傳思  派博傳思旗下網(wǎng)站  友情鏈接
派博傳思介紹 公司地理位置 論文服務(wù)流程 影響因子官網(wǎng) 吾愛論文網(wǎng) 大講堂 北京大學(xué) Oxford Uni. Harvard Uni.
發(fā)展歷史沿革 期刊點(diǎn)評 投稿經(jīng)驗(yàn)總結(jié) SCIENCEGARD IMPACTFACTOR 派博系數(shù) 清華大學(xué) Yale Uni. Stanford Uni.
QQ|Archiver|手機(jī)版|小黑屋| 派博傳思國際 ( 京公網(wǎng)安備110108008328) GMT+8, 2025-10-14 01:11
Copyright © 2001-2015 派博傳思   京公網(wǎng)安備110108008328 版權(quán)所有 All rights reserved
快速回復(fù) 返回頂部 返回列表
汝州市| 桃源县| 柳江县| 明光市| 南宁市| 酉阳| 长宁县| 绥棱县| 浮梁县| 长沙县| 茌平县| 高唐县| 西平县| 潢川县| 永济市| 金华市| 巴彦淖尔市| 连州市| 信阳市| 扎囊县| 鄄城县| 琼结县| 彰武县| 威远县| 杭州市| 天柱县| 林口县| 六盘水市| 扬州市| 富源县| 巴楚县| 宁安市| 扬中市| 仪征市| 云梦县| 兰西县| 苏州市| 桑植县| 庆云县| 淅川县| 泰安市|