Filters








6,115 Hits in 5.6 sec

Geometry and Expressive Power of Conditional Restricted Boltzmann Machines [article]

Guido Montufar, Nihat Ay, Keyan Ghazi-Zahedi
<span title="2015-03-12">2015</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Conditional restricted Boltzmann machines are undirected stochastic neural networks with a layer of input and output units connected bipartitely to a layer of hidden units.  ...  We address the representational power of these models, proving results their ability to represent conditional Markov random fields and conditional distributions with restricted supports, the minimal size  ...  M. and K. G.-Z. would like to thank the Santa Fe Institute for hosting them during the initial work on this article.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1402.3346v3">arXiv:1402.3346v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2ua4kbjq6jghvdjkvxpg7a45t4">fatcat:2ua4kbjq6jghvdjkvxpg7a45t4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200903100811/https://arxiv.org/pdf/1402.3346v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/16/c7/16c7993edd7fa464f6581c726a152190274f3d85.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1402.3346v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

AdS/CFT as a deep Boltzmann machine [article]

Koji Hashimoto
<span title="2019-03-12">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We provide a deep Boltzmann machine (DBM) for the AdS/CFT correspondence.  ...  Under the philosophy that the bulk spacetime is a neural network, we give a dictionary between those, and obtain a restricted DBM as a discretized bulk scalar field theory in curved geometries.  ...  Due to the hidden variables, the representation power of the restricted Boltzmann machines is greater.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.04951v1">arXiv:1903.04951v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5jtwkdz5sffe3fej7dutruwr4m">fatcat:5jtwkdz5sffe3fej7dutruwr4m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902000156/https://arxiv.org/pdf/1903.04951v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c9/91/c991f543e410a5cc1d3231b44d60825fbe4cff87.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.04951v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Emotional facial expression transfer based on temporal restricted Boltzmann machines

Shuojun Liu, Dong-Yan Huang, Weisi Lin, Minghui Dong, Haizhou Li, Ee Ping Ong
<span title="">2014</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/uwvzhxfa7jcfte6a2nokf6fbm4" style="color: black;">Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific</a> </i> &nbsp;
In this paper, we apply a temporal restricted Boltzmann machines based model to emotional facial expression transfer.  ...  The method can encode a complex nonlinear mapping from the motion of one neutral facial expression to another emotional facial expression which captures facial geometry and dynamics of both neutral state  ...  We review the temporal restricted Boltzmann machine and the inputoutput temporal restricted Boltzmann machine (IOTRBM) which extends the architecture to model an output sequence conditional on an input  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/apsipa.2014.7041738">doi:10.1109/apsipa.2014.7041738</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/apsipa/LiuHLDLO14.html">dblp:conf/apsipa/LiuHLDLO14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3mdrpzr7kfdr3hbctv5ixf27ay">fatcat:3mdrpzr7kfdr3hbctv5ixf27ay</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170830064438/http://www.apsipa.org/proceedings_2014/Data/paper/1311.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e3/bd/e3bd3911c13b807f6942f3d6ea831f0516cb8f37.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/apsipa.2014.7041738"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Neural-Network Quantum States, String-Bond States, and Chiral Topological States

Ivan Glasser, Nicola Pancotti, Moritz August, Ivan D. Rodriguez, J. Ignacio Cirac
<span title="2018-01-11">2018</span> <i title="American Physical Society (APS)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/34iggvr2oraezibenzxlccincy" style="color: black;">Physical Review X</a> </i> &nbsp;
In particular we demonstrate that short-range Restricted Boltzmann Machines are Entangled Plaquette States, while fully connected Restricted Boltzmann Machines are String-Bond States with a nonlocal geometry  ...  These results shed light on the underlying architecture of Restricted Boltzmann Machines and their efficiency at representing many-body quantum states.  ...  In particular, state-of-the-art numerical results have been obtained on popular models with restricted Boltzmann machines (RBM), and recent effort has demonstrated the power of deep Boltzmann machines  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1103/physrevx.8.011006">doi:10.1103/physrevx.8.011006</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3xmckawasjcl5bcai2cswt7nkm">fatcat:3xmckawasjcl5bcai2cswt7nkm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200313072206/https://pure.mpg.de/rest/items/item_2537561_2/component/file_2554067/content" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/20/dd/20dd019aa4528f95b30fe7a6da2f23b0c3e2d980.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1103/physrevx.8.011006"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> aps.org </button> </a>

Restricted Boltzmann Machines: Introduction and Review [article]

Guido Montufar
<span title="2018-06-19">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Restricted Boltzmann machines carry a rich structure, with connections to geometry, applied algebra, probability, statistics, machine learning, and other areas.  ...  The restricted Boltzmann machine is a network of stochastic units with undirected interactions between pairs of visible and hidden units.  ...  I am grateful to Nihat Ay, Johannes Rauh, Jason Morton, and more recently Anna Seigal for our collaborations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.07066v1">arXiv:1806.07066v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jwlx44dwevhv5hqym7znflqrvm">fatcat:jwlx44dwevhv5hqym7znflqrvm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901172522/https://arxiv.org/pdf/1806.07066v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e8/49/e8492fb2fb81d9c045a2ac582e25f7f483017a31.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.07066v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Restricted Boltzmann Machines: Introduction and Review [chapter]

Guido Montúfar
<span title="">2018</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/utbcqkmmffdmxnj3p5huqi5vkq" style="color: black;">Springer Proceedings in Mathematics &amp; statistics</a> </i> &nbsp;
A restricted Boltzmann machine (RBM) is a special type of a Boltzmann machine where the pair interactions are restricted to be between an observed set of units and an unobserved set of units.  ...  Restricted Boltzmann machines carry a rich structure, with connections to geometry, applied algebra, probability, statistics, machine learning, and other areas.  ...  I am grateful to Nihat Ay, Johannes Rauh, Jason Morton, and more recently Anna Seigal for our collaborations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-97798-0_4">doi:10.1007/978-3-319-97798-0_4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6nhgwspkybco5jgw7azfp4u6ly">fatcat:6nhgwspkybco5jgw7azfp4u6ly</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200319094200/https://www.mis.mpg.de/preprints/2018/preprint2018_87.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/30/33/303360442072fcf7b29aa7cceec09284a0ef0eb5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-97798-0_4"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Machine learning spatial geometry from entanglement features

Yi-Zhuang You, Zhao Yang, Xiao-Liang Qi
<span title="2018-01-31">2018</span> <i title="American Physical Society (APS)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/b7jx7xdhxncvtj2nb24xhplinq" style="color: black;">Physical review B</a> </i> &nbsp;
We show that each RTN can be mapped to a Boltzmann machine, trained by the entanglement entropies over all subregions of a given quantum many-body state.  ...  We demonstrate the EFL algorithm on 1D free fermion system and observe the emergence of the hyperbolic geometry (AdS_3 spatial geometry) as we tune the fermion system towards the gapless critical point  ...  Acknowledgments The authors would like to acknowledge the helpful discussions with Pan Zhang, Yanran Li, and Roger Melko.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1103/physrevb.97.045153">doi:10.1103/physrevb.97.045153</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/54dkvdov6bffbl642ovz63bs5i">fatcat:54dkvdov6bffbl642ovz63bs5i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190430044415/https://link.aps.org/accepted/10.1103/PhysRevB.97.045153" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b2/86/b286d7ffcf87809029973d090375693786e36343.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1103/physrevb.97.045153"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> aps.org </button> </a>

Geometry of the restricted Boltzmann machine [article]

Maria Angelica Cueto, Jason Morton, Bernd Sturmfels
<span title="2009-08-30">2009</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The restricted Boltzmann machine is a graphical model for binary random variables.  ...  We derive a dimension formula for the tropicalized model, and we use it to show that the restricted Boltzmann machine is identifiable in many cases.  ...  Acknowledgments We thank Jan Draisma, JM Landsberg, Honglak Lee, Sorgey Norin, Lior Pachter, Seth Sullivant, Ilya Sutskever, Jenia Tevelev, and Piotr Zwiernik for helpful discussions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/0908.4425v1">arXiv:0908.4425v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xtcoygatrbgnro7vqoycay4yky">fatcat:xtcoygatrbgnro7vqoycay4yky</a> </span>
<a target="_blank" rel="noopener" href="https://archive.org/download/arxiv-0908.4425/0908.4425.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> File Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/0908.4425v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Geometry and symmetry in the quantum Boltzmann machine

Hai-Jing Song, Tieling Song, Qi-Kai He, Yang Liu, D. L. Zhou
<span title="2019-04-03">2019</span> <i title="American Physical Society (APS)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/z3u6fzrh4fdvhnzujueyvzipwi" style="color: black;">Physical Review A</a> </i> &nbsp;
Quantum Boltzmann machine extends the classical Boltzmann machine learning to the quantum regime, which makes its power to simulate the quantum states beyond the classical probability distributions.  ...  We develop the BFGS algorithm to study the corresponding optimization problem in quantum Boltzmann machine, especially focus on the target states being a family of states with parameters.  ...  For the states |ψ(1, φ) , the hidden subsystem does not increase the power of the quantum Boltzmann machine.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1103/physreva.99.042307">doi:10.1103/physreva.99.042307</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4m5gydd2ffhb7cf732kiqxm4i4">fatcat:4m5gydd2ffhb7cf732kiqxm4i4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824234155/https://arxiv.org/pdf/1808.04567v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/05/d9/05d9d0153b17d7e835d0b5d282eed71fff2dbb9e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1103/physreva.99.042307"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> aps.org </button> </a>

Alternating minimization and Boltzmann machine learning

W. Byrne
<span title="">1992</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/22mhkeaq5zdqlmtti5oidj26fi" style="color: black;">IEEE Transactions on Neural Networks</a> </i> &nbsp;
Paining a Boltzmann machine with hidden units is appropriately treated in information geometry using the information divergence and the technique of alternating minimization.  ...  The resulting algorithm is shown to be closely related to gradient descent Boltzmann machine learning rules, and the close relationship of both to the EM algorithm is described.  ...  Boltzmann machines are not powerful enough without hidden units, and if a machine has hidden units, the correct behavior of the hidden units is usually unknown.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/72.143375">doi:10.1109/72.143375</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/18276461">pmid:18276461</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/c6xk34xyjfaffdr46qysaw7d4y">fatcat:c6xk34xyjfaffdr46qysaw7d4y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170921232455/http://svr-www.eng.cam.ac.uk/~wjb31/ppubs/TransNNAltMinBM.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/11/fc/11fcb64e0a9e0f4eb06da9379e428a4a9654f1e3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/72.143375"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Deep Narrow Boltzmann Machines are Universal Approximators [article]

Guido Montufar
<span title="2015-04-10">2015</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
belief networks and restricted Boltzmann machines, with respect to the currently available bounds for those models.  ...  We show that deep narrow Boltzmann machines are universal approximators of probability distributions on the activities of their visible units, provided they have sufficiently many hidden layers, each containing  ...  For the shallow layered version of the Boltzmann machine, called restricted Boltzmann machine (RBM) (Smolensky 1986; Freund & Haussler 1991) , the universal approximation capability has been shown in  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1411.3784v3">arXiv:1411.3784v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/evzdfnmd5femrdaxrpumzi5kba">fatcat:evzdfnmd5femrdaxrpumzi5kba</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824154450/https://arxiv.org/pdf/1411.3784v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4e/35/4e353081eb7242f94737de917f508d903b599e0d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1411.3784v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Entanglement Area Law for Shallow and Deep Quantum Neural Network States [article]

Zhih-Ahn Jia, Lu Wei, Yu-Chun Wu, Guang-Can Guo, Guo-Ping Guo
<span title="2020-03-08">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
By introducing the notion of local quasi-product states, for which the locally connected shallow feed-forward neural network states and restricted Boltzmann machine states are special cases, we show that  ...  Besides, we also investigate the entanglement features of deep Boltzmann machine states and show that locality constraints imposed on the neural networks make the states obey the entanglement area law.  ...  Jia acknowledges Zhenghan Wang and the math department of UCSB for hospitality.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.11333v2">arXiv:1907.11333v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/g4vgey5oybhsdfilpmcwk5uody">fatcat:g4vgey5oybhsdfilpmcwk5uody</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320160508/https://arxiv.org/pdf/1907.11333v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.11333v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Hierarchical Models as Marginals of Hierarchical Models [article]

Guido Montufar, Johannes Rauh
<span title="2016-03-07">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In particular, we show that a restricted Boltzmann machine with less than [ 2((v)+1) / (v+1) ] 2^v-1 hidden binary variables can approximate every distribution of v visible binary variables arbitrarily  ...  We focus on binary variables and marginals of pairwise interaction models whose hidden variables are conditionally independent given the visible variables.  ...  The representational power of restricted Boltzmann machines has been studied assiduously; see, e.g., [3, 17, 7, 10] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1508.03606v2">arXiv:1508.03606v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pnspzaozhjcmjllhzjchf3dzza">fatcat:pnspzaozhjcmjllhzjchf3dzza</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827191337/https://arxiv.org/pdf/1508.03606v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4c/33/4c33d035096104d1a1cc38834e23cc5fd74fcce7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1508.03606v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

From probabilistic graphical models to generalized tensor networks for supervised learning [article]

Ivan Glasser, Nicola Pancotti, J. Ignacio Cirac
<span title="2019-12-03">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The models we consider also have a natural implementation on a quantum computer and may guide the development of near-term quantum machine learning architectures.  ...  Tensor networks have found a wide use in a variety of applications in physics and computer science, recently leading to both theoretical insights as well as practical algorithms in machine learning.  ...  ACKNOWLEDGMENT We would like to thank Shi-ju Ran, Yoav Levine and Miles Stoudenmire for discussions, as well as Vedran Dunjko for a careful reading of the paper and helpful comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.05964v2">arXiv:1806.05964v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/b62plq223rappb5p6fll76o6li">fatcat:b62plq223rappb5p6fll76o6li</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928145801/https://arxiv.org/pdf/1806.05964v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a3/6c/a36cc4c033d04e4a7603280cf2cf7f99c7e4f434.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.05964v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

From Probabilistic Graphical Models to Generalized Tensor Networks for Supervised Learning

Ivan Glasser, Nicola Pancotti, J. Ignacio Cirac.
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
The models we consider also have a natural implementation on a quantum computer and may guide the development of near-term quantum machine learning architectures.  ...  Tensor networks have found a wide use in a variety of applications in physics and computer science, recently leading to both theoretical insights as well as practical algorithms in machine learning.  ...  ACKNOWLEDGMENT We would like to thank Shi-Ju Ran, Yoav Levine, and Miles Stoudenmire for discussions, and Vedran Dunjko for a careful reading of the paper and helpful comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2986279">doi:10.1109/access.2020.2986279</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/b22uwdtlwjgujdgwmeue2mqrt4">fatcat:b22uwdtlwjgujdgwmeue2mqrt4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108184909/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09058650.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/24/96/2496140b7eed399f447921a6c7e0f248be1647df.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2986279"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 6,115 results