{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:21Z","timestamp":1760245041365,"version":"3.37.3"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2018,5,1]],"date-time":"2018-05-01T00:00:00Z","timestamp":1525132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Chinese 863 Program","award":["2015AA015403"],"award-info":[{"award-number":["2015AA015403"]}]},{"DOI":"10.13039\/501100006606","name":"Key Project of Tianjin Natural Science Foundation","doi-asserted-by":"publisher","award":["15JCZDJC31100"],"award-info":[{"award-number":["15JCZDJC31100"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Tianjin Younger Natural Science Foundation","doi-asserted-by":"publisher","award":["14JCQNJC00400"],"award-info":[{"award-number":["14JCQNJC00400"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Project of Chinese National Social Science Fund","award":["14ZDB153"],"award-info":[{"award-number":["14ZDB153"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/tnnls.2017.2664100","type":"journal-article","created":{"date-parts":[[2017,3,16]],"date-time":"2017-03-16T23:12:23Z","timestamp":1489705943000},"page":"1608-1621","source":"Crossref","is-referenced-by-count":6,"title":["A Confident Information First Principle for Parameter Reduction and Model Selection of Boltzmann Machines"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4391-1416","authenticated-orcid":false,"given":"Xiaozhao","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3238-493X","authenticated-orcid":false,"given":"Yuexian","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7360-8864","authenticated-orcid":false,"given":"Wenjie","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-20192-9"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177012480"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/72.125867"},{"journal-title":"Methods of Information Geometry","year":"1993","author":"amari","key":"ref32"},{"journal-title":"A survey of dimensionality reduction techniques","year":"2014","author":"sorzano","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2172\/15002155"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2493175.2493177"},{"key":"ref36","first-page":"81","article-title":"Information and accuracy attainable in the estimation of statistical parameters","volume":"37","author":"rao","year":"1945","journal-title":"Bull Calcutta Math Soc"},{"journal-title":"Statistical Decision Rules and Optimal Inference","year":"1982","author":"?encov","key":"ref35"},{"journal-title":"Algebraic and Geometric Methods in Statistics","year":"2010","author":"gibilisco","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390224"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/e16073670"},{"key":"ref11","first-page":"1409","article-title":"Generative versus discriminative training of RBMs for classification of FMRI images","author":"schmah","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.01.006"},{"key":"ref13","first-page":"625","article-title":"Why does unsupervised pre-training help deep learning?","volume":"11","author":"erhan","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1006\/jmps.1999.1276"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolmodel.2007.10.030"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1974.1100705"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176344136"},{"journal-title":"Pattern Recognition and Machine Learning","year":"2007","author":"bishop","key":"ref18"},{"key":"ref19","first-page":"419","article-title":"Information geometry approach to the model selection of neural networks","volume":"3","author":"lv","year":"2006","journal-title":"Proc 1st Int Conf Innov Comput Inf Control (ICICIC)"},{"key":"ref28","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"guyon","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref4","first-page":"153","article-title":"Greedy layer-wise training of deep networks","author":"bengio","year":"2006","journal-title":"Proc NIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1142\/9781860945410_0007"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00311"},{"key":"ref6","first-page":"1121","article-title":"Modeling image patches with a directed hierarchy of Markov random field","author":"osindero","year":"2007","journal-title":"Proc NIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btm344"},{"key":"ref5","first-page":"1137","article-title":"Efficient learning of sparse representations with an energy-based model","author":"ranzato","year":"2006","journal-title":"Proc NIPS"},{"key":"ref8","first-page":"1249","article-title":"Using deep belief nets to learn covariance kernels for Gaussian processes","author":"salakhutdinov","year":"2007","journal-title":"Proc NIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref2","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref9","first-page":"89","article-title":"Semantic hashing","author":"salakhutdinov","year":"2007","journal-title":"Proc SIGIR Workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/08997660260293238"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1890\/13-0590.1"},{"key":"ref45","first-page":"1","article-title":"Understanding deep learning by revisiting Boltzmann machines: An information geometry approach","volume":"abs 1302 3931","author":"zhao","year":"2013","journal-title":"CoRR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16354-3_73"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_41"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.1946.0056"},{"key":"ref21","first-page":"175","article-title":"On the use and interpretation of certain test criteria for purposes of statistical inference: Part I","volume":"20a","author":"neyman","year":"1928","journal-title":"Biometrika"},{"key":"ref42","first-page":"17","article-title":"On contrastive divergence learning","volume":"10","author":"carreira-perpinan","year":"2005","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"tibshirani","year":"1996","journal-title":"J Roy Statist Soc B Statist Methodol"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0901_7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS054"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(95)00003-8"},{"journal-title":"Model Selection and Multi-Model Inference A Practical Information-Theoretic Approach","year":"2003","author":"burnhan","key":"ref26"},{"journal-title":"Markov Chain Monte Carlo in Practice","year":"1996","author":"gilks","key":"ref43"},{"key":"ref25","first-page":"2541","article-title":"On model selection consistency of Lasso","volume":"7","author":"zhao","year":"2006","journal-title":"J Mach Learn Res"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8338465\/07879831.pdf?arnumber=7879831","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T02:05:58Z","timestamp":1719108358000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7879831\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":48,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2017.2664100","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2018,5]]}}}