Filters








2,606 Hits in 7.2 sec

Maximum Margin Decision Surfaces for Increased Generalisation in Evolutionary Decision Tree Learning [chapter]

Alexandros Agapitos, Michael O'Neill, Anthony Brabazon, Theodoros Theodoridis
<span title="">2011</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
Decision tree learning is one of the most widely used and practical methods for inductive inference.  ...  The evolutionary optimisation concerns maximising the decision-surface margin that is defined to be the smallest distance between the decisionsurface and any of the samples.  ...  SVMs to reduce the upper bound on the expected generalisation error.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-20407-4_6">doi:10.1007/978-3-642-20407-4_6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/73724d2yljf7lhfejx6wtafeja">fatcat:73724d2yljf7lhfejx6wtafeja</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180720135544/https://researchrepository.ucd.ie/bitstream/10197/3493/1/CameraReady.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/d6/7e/d67e34c6f5d3cacdffce04af7f39618c5f21cba0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-20407-4_6"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Using evolutionary Expectation Maximization to estimate indel rates

I. Holmes
<span title="2005-02-24">2005</span> <i title="Oxford University Press (OUP)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wmo54ba2jnemdingjj4fl3736a" style="color: black;">Bioinformatics</a> </i> &nbsp;
mutation rates of the underlying evolutionary model (to facilitate the development of stochastic grammars based on phylogenetic trees, also known as Statistical Alignment).  ...  Motivation: The Expectation Maximisation algorithm, in the form of the Baum-Welch algorithm (for HMMs) or the Inside-Outside algorithm (for SCFGs), is a powerful way to estimate the parameters of stochastic  ...  The author would like to thank Bob Griffiths, Von Bing Yap and Terry Speed for helpful discussions, and two anonymous reviewers for their suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1093/bioinformatics/bti177">doi:10.1093/bioinformatics/bti177</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/15731213">pmid:15731213</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/74vrtqjx5vgxfkr54eibo46vz4">fatcat:74vrtqjx5vgxfkr54eibo46vz4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20120124190018/http://biowiki.org/~yam/Papers/Holmes2005-IndelRateEM.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/5d/69/5d69ea395ae197543db8d50da64cf7ea9ff305ef.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1093/bioinformatics/bti177"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> oup.com </button> </a>

DHOG: Deep Hierarchical Object Grouping [article]

Luke Nicholas Darlow, Amos Storkey
<span title="2020-03-13">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We obtain accuracy improvements of: 4.3% on CIFAR-10, 1.5% on CIFAR-100-20, and 7.2% on SVHN.  ...  The resulting representations are then invariant to stochastic augmentation strategies, and can be used for downstream tasks such as clustering or classification.  ...  Acknowledgements This work was supported in part by the EPSRC Centre for Doctoral Training in Data Science, funded by the UK Engineering and Physical Sciences Research Council (grant EP/L016427/1) and  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.08821v1">arXiv:2003.08821v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hazqf6zkkrcn3odykqogxfnui4">fatcat:hazqf6zkkrcn3odykqogxfnui4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200323003156/https://arxiv.org/pdf/2003.08821v1.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/2003.08821v1" 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>

An expectation maximization algorithm for training hidden substitution models 1 1Edited by F. Cohen

I. Holmes, G.M. Rubin
<span title="">2002</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/nk6zopmzsjfizb6z5kztdu477y" style="color: black;">Journal of Molecular Biology</a> </i> &nbsp;
We used the algorithm to train hidden substitution matrices on protein alignments in the Pfam database.  ...  We derive an expectation maximization algorithm for maximum-likelihood training of substitution rate matrices from multiple sequence alignments.  ...  One of us (I.H.H.) especially thanks Eliza McKenna for support and encouragement.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1006/jmbi.2002.5405">doi:10.1006/jmbi.2002.5405</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/11955022">pmid:11955022</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xj6xow3lt5bo7cts52bt7qs2ey">fatcat:xj6xow3lt5bo7cts52bt7qs2ey</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20120124190029/http://biowiki.org/~yam/Papers/HolmesRubin2002-RateMatrixEM.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/2f/d0/2fd015d334d0ef7314f64d5d8dcc54c943c76932.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1006/jmbi.2002.5405"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Exploiting First-Order Regression in Inductive Policy Selection [article]

Charles Gretton, Sylvie Thiebaux
<span title="2012-07-11">2012</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This approach avoids the more complex reasoning of symbolic dynamic programming while focusing the inductive solver's attention on concepts that are specifically relevant to the optimal value function  ...  The latter reason about the optimal value function using first-order decision theoretic regression and formula rewriting, while the former, when provided with a suitable hypotheses language, are capable  ...  Acknowledgements Thanks to Doug Aberdeen, Joshua Cole, Bob Givan, John Lloyd, Kee Siong Ng, and John Slaney for useful discussions, and to the anonymous reviewers for their suggestions on how to improve  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1207.4107v1">arXiv:1207.4107v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kactt3saibcfhjprok43ab3p6q">fatcat:kactt3saibcfhjprok43ab3p6q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826021656/https://arxiv.org/ftp/arxiv/papers/1207/1207.4107.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/9e/13/9e13972d87ced0c47650c182960bced8fdf6a05a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1207.4107v1" 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>

Sample-Efficient, Exploration-Based Policy Optimisation for Routing Problems [article]

Nasrin Sultana, Jeffrey Chan, Tabinda Sarwar, A. K. Qin
<span title="2022-05-31">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In addition, we design an off-policy-based reinforcement learning technique that maximises the expected return and improves the sample efficiency to achieve faster learning during training time.  ...  The Empirical results show that the proposed method can improve on state-of-the-art methods in terms of solution quality and computation time and generalise to problems of different sizes.  ...  Euclidean distance to calculate the distance between two cities, and the objective was to minimise the total travel distance.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.15656v1">arXiv:2205.15656v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sxsfdy3exbfxnpwyqexub5tml4">fatcat:sxsfdy3exbfxnpwyqexub5tml4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220610081244/https://arxiv.org/pdf/2205.15656v1.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/d6/a7/d6a70ee6911e9ec2c4fc9706082147daf5015745.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.15656v1" 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>

Detecting repeated cancer evolution from multi-region tumor sequencing data

Giulio Caravagna, Ylenia Giarratano, Daniele Ramazzotti, Ian Tomlinson, Trevor A. Graham, Guido Sanguinetti, Andrea Sottoriva
<span title="2018-08-31">2018</span> <i title="Springer Nature America, Inc"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/l6cw2tyvgrhytbvantrj2os37y" style="color: black;">Nature Methods</a> </i> &nbsp;
We developed a machine-learning method based on transfer learning that allowed us to overcome the stochastic effects of cancer evolution and noise in data and identified hidden evolutionary patterns in  ...  Our method provides a means of classifying patients on the basis of how their tumor evolved, with implications for the anticipation of disease progression.  ...  The structural correlation among each model is measured via a parameter w, which we maximise.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1038/s41592-018-0108-x">doi:10.1038/s41592-018-0108-x</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/30171232">pmid:30171232</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC6380470/">pmcid:PMC6380470</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mb2rgecifjb7pfts7gytyhhckq">fatcat:mb2rgecifjb7pfts7gytyhhckq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200318162141/https://www.research.ed.ac.uk/portal/files/70385845/REVOLVER_MainText.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/a6/55/a6551105299976db9628dd163025bf6a6955f8c4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1038/s41592-018-0108-x"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> nature.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6380470" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories [article]

Christopher W. F. Parsonson, Alexandre Laterre, Thomas D. Barrett
<span title="2022-05-28">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In experiments on four combinatorial tasks, our approach enables learning-to-branch without any expert guidance or pre-training.  ...  The canonical branch-and-bound (B&B) algorithm seeks to exactly solve MILPs by constructing a search tree of increasingly constrained sub-problems.  ...  ∈ [0, 1] a factor by which to discount expected future returns to their present value.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.14345v1">arXiv:2205.14345v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6s5liouyvzfb7lubp472zg57xu">fatcat:6s5liouyvzfb7lubp472zg57xu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220605164819/https://arxiv.org/pdf/2205.14345v1.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/73/63/73638f8110b65619b1a0e8da7b0d4b19bb33dc7b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.14345v1" 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>

Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly [article]

Kirthevasan Kandasamy, Karun Raju Vysyaraju, Willie Neiswanger, Biswajit Paria, Christopher R. Collins, Jeff Schneider, Barnabas Poczos, Eric P. Xing
<span title="2020-04-19">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Additionally, we develop new methodological improvements in BO for selecting the Bayesian model, selecting the acquisition function, and optimising over complex domains with different variable types and  ...  We compare Dragonfly to a suite of other packages and algorithms for global optimisation and demonstrate that when the above methods are integrated, they enable significant improvements in the performance  ...  We thank Anthony Yu, Shuli Jiang, and Shalom Yiblet for assisting with the development of Dragonfly.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.06694v2">arXiv:1903.06694v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cq3fgwmcufbg7cib626uabypr4">fatcat:cq3fgwmcufbg7cib626uabypr4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200503052038/https://arxiv.org/pdf/1903.06694v2.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/1903.06694v2" 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>

INSPIRE: Intensity and Spatial Information-Based Deformable Image Registration [article]

Johan Öfverstedt, Joakim Lindblad, Nataša Sladoje
<span title="2020-12-14">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
INSPIRE extends our existing symmetric registration framework based on distances combining intensity and spatial information to an elastic B-splines based transformation model.  ...  We also present several theoretical and algorithmic improvements which provide high computational efficiency and thereby applicability of the framework in a wide range of real scenarios.  ...  ACKNOWLEDGMENT The authors would like to thank Marc Niethammer for assistance with the pre-processing of the datasets LPBA40, IBSR18, CUMC12, and MGH10, as well as the research groups and institutions  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.07208v1">arXiv:2012.07208v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ybpn2vrenzho7eslk4k3fcddkm">fatcat:ybpn2vrenzho7eslk4k3fcddkm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201218035505/https://arxiv.org/pdf/2012.07208v1.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/44/a5/44a504cecc37643c535eae6380e260101dd0d3de.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.07208v1" 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>

Dopamine-modulated dynamic cell assemblies generated by the GABAergic striatal microcircuit

Mark D. Humphries, Ric Wood, Kevin Gurney
<span title="">2009</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/oml24fsyizfuhn3rn5np75ubdi" style="color: black;">Neural Networks</a> </i> &nbsp;
of synchronisation is strongly dependent on the simulated concentration of dopamine.  ...  It receives convergent input from all over neocortex, hippocampal formation, amygdala and thalamus, and is the primary recipient of dopamine in the brain.  ...  ; FSI axonal connections on MSN dendritic trees; FSI axonal connections on FSI dendritic trees; and gap junctions between FSI dendritic trees.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.neunet.2009.07.018">doi:10.1016/j.neunet.2009.07.018</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/19646846">pmid:19646846</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kbpqaxu4xfcsxnk2o3n7ev6i6e">fatcat:kbpqaxu4xfcsxnk2o3n7ev6i6e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160806104244/http://eprints.whiterose.ac.uk:80/10120/1/Humphries1.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/8c/6f/8c6f2e596591bafeb954c41076f556135ac8e596.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.neunet.2009.07.018"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Dopamine-modulated dynamic cell assemblies generated by the GABAergic striatal microcircuit

Gurney Kevin
<span title="">2010</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wrk3kouosrhcxiprcbguskdipu" style="color: black;">Frontiers in Neuroscience</a> </i> &nbsp;
of synchronisation is strongly dependent on the simulated concentration of dopamine.  ...  It receives convergent input from all over neocortex, hippocampal formation, amygdala and thalamus, and is the primary recipient of dopamine in the brain.  ...  ; FSI axonal connections on MSN dendritic trees; FSI axonal connections on FSI dendritic trees; and gap junctions between FSI dendritic trees.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/conf.fnins.2010.03.00238">doi:10.3389/conf.fnins.2010.03.00238</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cvtpbha62zat3noxjnukt6v4gq">fatcat:cvtpbha62zat3noxjnukt6v4gq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160806104244/http://eprints.whiterose.ac.uk:80/10120/1/Humphries1.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/8c/6f/8c6f2e596591bafeb954c41076f556135ac8e596.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/conf.fnins.2010.03.00238"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a>

Learning to track environment state via predictive autoencoding [article]

Marian Andrecki, Nicholas K. Taylor
<span title="2021-12-14">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The network can output both expectation over future observations and samples from belief distribution. The resulting functionalities are similar to those of a Particle Filter (PF).  ...  This work introduces a neural architecture for learning forward models of stochastic environments.  ...  Using terms from Section 2, the environment is stochastic and partially-observable via intermittent and noisy unstructured percepts. The network was trained using purely time series of observations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.07745v1">arXiv:2112.07745v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ehhqc4cmyfdjlgmhra3yh4v7wi">fatcat:ehhqc4cmyfdjlgmhra3yh4v7wi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211225212833/https://arxiv.org/pdf/2112.07745v1.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/0b/f7/0bf77ad0927b700f5d358c83caa3cf40961403ae.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.07745v1" 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>

Optimal Bayesian design for model discrimination via classification [article]

Markus Hainy, David J. Price, Olivier Restif, Christopher Drovandi
<span title="2019-07-10">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
DJP and OR were supported by research grant BB/M020193/1 from the Biotechnology and Biological Science Research Council (UK).  ...  Computational resources and services used in this work were provided by the HPC and Research Support Group, Queensland University of Technology, Brisbane, Australia.  ...  Then the goal is to maximise the expected utility function.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.05301v2">arXiv:1809.05301v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/d5qiab3na5ctnffbyhm35zwm3a">fatcat:d5qiab3na5ctnffbyhm35zwm3a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929230811/https://arxiv.org/pdf/1809.05301v1.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/15/6c/156cddff135653074bfa69615e8bab2ffdc85223.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.05301v2" 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>

Bayesian Distributional Policy Gradients [article]

Luchen Li, A. Aldo Faisal
<span title="2021-03-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
exploitation and policy learning in general.  ...  This enables us to translate successful conventional RL algorithms that are based on state values into distributional RL.  ...  Acknowledgments We are grateful for our funding support: a Department of Computing PhD Award to LL and a UKRI Turing AI Fellowship (EP/V025449/1) to AAF.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.11265v2">arXiv:2103.11265v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f5ykig2iqvbixblazqbsamo3nu">fatcat:f5ykig2iqvbixblazqbsamo3nu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210329122531/https://arxiv.org/pdf/2103.11265v2.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/db/5e/db5ec14be596e3c52cd2fa29473927cb70239973.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.11265v2" 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>
&laquo; Previous Showing results 1 &mdash; 15 out of 2,606 results