Filters








3,100 Hits in 4.9 sec

Efficient variational Bayesian neural network ensembles for outlier detection [article]

Nick Pawlowski, Miguel Jaques, Ben Glocker
<span title="2017-04-22">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work we perform outlier detection using ensembles of neural networks obtained by variational approximation of the posterior in a Bayesian neural network setting.  ...  We show our outlier detection results are comparable to those obtained using other efficient ensembling methods.  ...  ACKNOWLEDGEMENTS NP is supported by Microsoft Research through its PhD Scholarship Programme and the EPSRC Centre for Doctoral Training in High Performance Embedded and Distributed Systems (HiPEDS, Grant  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.06749v2">arXiv:1703.06749v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sobb2mhh55afna2rqw44czvty4">fatcat:sobb2mhh55afna2rqw44czvty4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824211317/https://arxiv.org/pdf/1703.06749v2.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/39/ef/39efb13b0324f78c02b7e9f8d0bd5315f251004d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.06749v2" 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 Approximate Bayesian Long Short-Term Memory Algorithm for Outlier Detection [article]

Chao Chen, Xiao Lin, Gabriel Terejanu
<span title="2019-06-04">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, exact Bayesian neural network methods are intractable and non-applicable for real-world applications.  ...  To assess the proposed algorithm, we apply it to outlier detection in five real-world events retrieved from the Twitter platform.  ...  The MC dropout model, however, has the worst performance for this specific outlier detection task.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1712.08773v2">arXiv:1712.08773v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h5icrg7hm5axfan7logxrgsduu">fatcat:h5icrg7hm5axfan7logxrgsduu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825071241/https://arxiv.org/pdf/1712.08773v1.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/55/e7/55e79ed0a7daa2c3351d746fc6730f2c13e92555.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1712.08773v2" 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>

Evaluation of Uncertainty Quantification in Deep Learning [chapter]

Niclas Ståhl, Göran Falkman, Alexander Karlsson, Gunnar Mathiason
<span title="">2020</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jyopc6cf5ze5vipjlm4aztcffi" style="color: black;">Communications in Computer and Information Science</a> </i> &nbsp;
Both the Bayesian neural network and the ensemble of neural networks do, for example, pick up the curvy shape of a "B" and interpret this as the digit "3" and, hence, the models are certain of the output  ...  (Color figure online) The distribution of the quantified uncertainty for the different methods, split up into aleatoric and epistemic uncertainty for the Bayesian neural network and the ensemble of neural  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-50146-4_41">doi:10.1007/978-3-030-50146-4_41</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ajfgdtyz2jbsfe3kph2gplpmly">fatcat:ajfgdtyz2jbsfe3kph2gplpmly</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200815052225/https://link.springer.com/content/pdf/10.1007%2F978-3-030-50146-4_41.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/4f/86/4f8690e5db4ae32b8df9d320cd3091f04e6ab357.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-50146-4_41"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Generative Particle Variational Inference via Estimation of Functional Gradients [article]

Neale Ratzlaff, Qinxun Bai, Li Fuxin, Wei Xu
<span title="2021-08-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Recently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in variational inference.  ...  This work proposes a new method for learning to approximately sample from the posterior distribution.  ...  For example, a recent case of interest is Bayesian neural networks (BNNs), which applies Bayesian inference to deep neural network training in order to provide a principled way to assess model uncertainty  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.01291v2">arXiv:2103.01291v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7dhvd2ckvjf5bk7zuj2nl3xw6i">fatcat:7dhvd2ckvjf5bk7zuj2nl3xw6i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210815152006/https://arxiv.org/pdf/2103.01291v2.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/32/ec/32ec238feec8ce1ff18c8220b6043e57ba45bdf1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.01291v2" 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>

Variational Gaussian Mixture Models with robust Dirichlet concentration priors for virtual population generation in hypertrophic cardiomyopathy: a comparison study

Vasileios C. Pezoulas, Grigorios I. Grigoriadis, Nikolaos S. Tachos, Fausto Barlocco, Iacopo Olivotto, Dimitrios I. Fotiadis
<span title="2021-12-09">2021</span> <i title="Zenodo"> Zenodo </i> &nbsp;
The proposed method was compared against state-of-the-art virtual data generators, such as, the Bayesian networks, the supervised tree ensembles (STE), the unsupervised tree ensembles (UTE), and the artificial  ...  In this work, we utilize Gaussian Mixture Models (GMM) with variational Bayesian inference (BGMM) using robust estimations of Dirichlet concentration priors for the generation of virtual populations.  ...  In this case, the variance is used for the selection of the splitting feature. 3) Artificial neural networks Artificial neural networks (ANNs) were also used for virtual population generation, where  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.6358957">doi:10.5281/zenodo.6358957</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5xjidhv5cbffvfojrmhsikzpty">fatcat:5xjidhv5cbffvfojrmhsikzpty</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220323141115/https://zenodo.org/record/6358958/files/paper_EMBC_2021_VP.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/fe/3a/fe3a8e25d5e7ea5f2f651639502608063eb159cf.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.6358957"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

NADS: Neural Architecture Distribution Search for Uncertainty Awareness [article]

Randy Ardywibowo, Shahin Boluki, Xinyu Gong, Zhangyang Wang, Xiaoning Qian
<span title="2020-06-11">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
With this formulation, we are able to optimize a stochastic OoD detection objective and construct an ensemble of models to perform OoD detection.  ...  To address these problems, we first seek to identify guiding principles for designing uncertainty-aware architectures, by proposing Neural Architecture Distribution Search (NADS).  ...  We also thank Texas A&M High Performance Research Computing and Texas Advanced Computing Center for providing computational resources to perform experiments in this work.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.06646v1">arXiv:2006.06646v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bqzwefudvvezjndhntvgzbs6lq">fatcat:bqzwefudvvezjndhntvgzbs6lq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200623154229/https://arxiv.org/pdf/2006.06646v1.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/d7/20/d72040267b43260e58c6df3a24f2d4de485da0ab.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.06646v1" 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>

A Survey of Uncertainty in Deep Neural Networks [article]

Jakob Gawlikowski, Cedrique Rovile Njieutcheu Tassi, Mohsin Ali, Jongseok Lee, Matthias Humt, Jianxiang Feng, Anna Kruspe, Rudolph Triebel, Peter Jung, Ribana Roscher, Muhammad Shahzad, Wen Yang (+2 others)
<span title="2022-01-18">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The modeling of these uncertainties based on deterministic neural networks, Bayesian neural networks, ensemble of neural networks, and test-time data augmentation approaches is introduced and different  ...  For a practical application, we discuss different measures of uncertainty, approaches for the calibration of neural networks and give an overview of existing baselines and implementations.  ...  bining principled Bayesian learning for deep neural networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.03342v3">arXiv:2107.03342v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cex5j3xq5fdijjdtdbt2ixralm">fatcat:cex5j3xq5fdijjdtdbt2ixralm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220127192259/https://arxiv.org/pdf/2107.03342v3.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/fc/70/fc70db46738fff97d9ee3d66c6f9c57794d7b4fa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.03342v3" 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>

Towards an Ensemble Regressor Model for Anomalous ISP Traffic Prediction [article]

Sajal Saha, Anwar Haque, Greg Sidebottom
<span title="2022-05-03">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, the intuitive approach of predicting network traffic using administrative experience and market analysis data is inadequate for an efficient forecast framework.  ...  Prediction of network traffic behavior is significant for the effective management of modern telecommunication networks.  ...  , deep learning model, e.g., DNN (Deep Neural Network), CNN(Convolutional Neural Network) or sequence model such RNN (Recurrent Neural Network), LSTM (Long Short Term Memory), etc.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.01300v1">arXiv:2205.01300v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/l2jalmyzivgdnl2dbng3hf6icm">fatcat:l2jalmyzivgdnl2dbng3hf6icm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220507234624/https://arxiv.org/pdf/2205.01300v1.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/3a/e9/3ae92c90702c74b506e1be3421670636c8c3a80d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.01300v1" 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>

Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priors [article]

Yibo Yang, Georgios Kissas, Paris Perdikaris
<span title="2022-03-06">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We adopt a frequentist approach based on randomized prior ensembles, and put forth an efficient vectorized implementation for fast parallel inference on accelerated hardware.  ...  We present a simple and effective approach for posterior uncertainty quantification in deep operator networks (DeepONets); an emerging paradigm for supervised learning in function spaces.  ...  for outliers.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.03048v1">arXiv:2203.03048v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lqxq7oo46fhhxlblbyb6ouu2xa">fatcat:lqxq7oo46fhhxlblbyb6ouu2xa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220309104822/https://arxiv.org/pdf/2203.03048v1.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/f9/e1/f9e1d481f92cc026a87ba76b4bec035168fff0dd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.03048v1" 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>

HyperGAN: A Generative Model for Diverse, Performant Neural Networks [article]

Neale Ratzlaff, Li Fuxin
<span title="2020-07-14">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We introduce HyperGAN, a new generative model for learning a distribution of neural network parameters.  ...  Standard neural networks are often overconfident when presented with data outside the training distribution.  ...  Generating parameters for neural networks is not strictly the purview of approximate Bayesian inference.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.11058v3">arXiv:1901.11058v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dgxgm7fhoraslkcc2ah7eswgxm">fatcat:dgxgm7fhoraslkcc2ah7eswgxm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200809012900/https://arxiv.org/pdf/1901.11058v3.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/1901.11058v3" 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>

Universal uncertainty estimation for nuclear detector signals with neural networks and ensemble learning [article]

Pengcheng Ai, Zhi Deng, Yi Wang, Chendi Shen
<span title="2022-01-23">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose using multi-layer convolutional neural networks for empirical uncertainty estimation and feature extraction of nuclear pulse signals.  ...  Furthermore, ensemble learning is utilized to estimate the uncertainty originated from trainable parameters of the network and improve the robustness of the whole model.  ...  of several deep neural networks to replace the complicated Bayesian network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.04975v3">arXiv:2110.04975v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/djvnpmf4rjg4bopbeejphzpjbm">fatcat:djvnpmf4rjg4bopbeejphzpjbm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220127222126/https://arxiv.org/pdf/2110.04975v3.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/ea/18/ea18dd0542dc8da7426bc221a459d022aab19081.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.04975v3" 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>

A computational pipeline for data augmentation towards the improvement of disease classification and risk stratification models: a case study in two clinical domains

Vasileios C. Pezoulas, Grigoris I. Grigoriadis, George Gkois, Nikolaos S. Tachos, Tim Smole, Zoran Bosnić, Matej Pičulin, Iacopo Olivotto, Fausto Barlocco, Marko Robnik-Šikonja, Djordje G. Jakovljevic, Andreas Goules (+2 others)
<span title="2021-06-06">2021</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wdwg5aetkjbgpga7kn2jevifmi" style="color: black;">Computers in Biology and Medicine</a> </i> &nbsp;
To do so, multivariate approaches, such as, the multivariate normal distribution (MVND), and straightforward ones, such as, the Bayesian networks, the artificial neural networks (ANNs), and the tree ensembles  ...  Our results revealed the favorable performance of the tree ensemble generators, in both domains, yielding virtual data with goodness-of-fit 0.021 and KL-divergence 0.029 in pSS and 0.029, 0.027 in HCM,  ...  This paper reflects only the author's view and the Commission is not responsible for any use that may be made of the information it contains.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.compbiomed.2021.104520">doi:10.1016/j.compbiomed.2021.104520</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/34118751">pmid:34118751</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6gf4hrrwxfh6ldjivvqbb334vu">fatcat:6gf4hrrwxfh6ldjivvqbb334vu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210608222851/https://pdf.sciencedirectassets.com/271150/AIP/1-s2.0-S0010482521003140/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEMb%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEaCXVzLWVhc3QtMSJHMEUCIAQ2DCvMuCH6%2F5as9zDmgTNTsRzo5CEPZXirErqWNIKQAiEAz1VU%2F8DbBVnHzm132ZTmWJaRaRcrTF%2FUREgXyFQtTu4q%2BgMIfxAEGgwwNTkwMDM1NDY4NjUiDEclRNi4rkQ1h9HYMyrXA0XFG2XiMwDWu%2BEIXkixT%2BcUEPwRZAwvzTVyRIqwkcr2V8zsObPUKYSAvqtAj6PLcNwYDmqPY9R7YwtwtBsQtrxTJAfZI06825pY7uzyJ3mfM2F%2F3zyp8a%2B0cqTrXCZIh%2FYXk5Le%2BlxBfcMXylsfRfMA1nG%2Fcita6V3kHwzZUmhPtCgW%2BpY%2Fxz9peX65CUdck6VH1tnWmZoK%2F8YLY9bkF4W99vW2OuTZkt4GDshctPipOYf5F74ArO9qNOZYXs1CBLClAptbSpC7SJVpEsFGKJZj%2B9d%2BVnqnVPxFHkozIOIjPbqtvfafHEc2pSqVCsKqMNlxsRMQLcdlb1o7kZ22gEfvuSCA9SI8LQqYi%2BVorBkYZL6xqJo0gUgNV32%2FsQ%2FoiYiufGKMiweCRfc%2Bk1dmlQ2hmDz81lWZ3ROnoNhtwkFpl7BfOv7TKAAXeCu31wa%2BaG%2FQ2XS0ZAeWCcjtGePbE0Mav2yXK9C1h68ECF%2F9Sx%2BLUbEWepyELRB6SRiaGEb4dUJqJBcifCT5G0elumBRpgnEg9Zf7%2FikKX0iV5nPTFCcxel6OMaHDmMGHbvXpig4AJAIJuA3h07OXWBI4fub5GtoLgU7oqqpuz%2BuKZNXZiv8JJoONhC3%2BDDRy%2F%2BFBjqlAdPHIVtbvYaYaf04K23FBuxF%2FDYnziArHmbTieR0uJpYs5RqDeGMuBVfURJ8a552Maq2w0IzlwgeP6KrSNjZ43WsvloQ2Uza4KxpASOnME7KbCn9wK6X%2BNiqm6h6frA7bz%2BFV0%2F1rIuNyy0Pp6%2Fe%2Beej7%2Bi2V1dO2UOJ6aSzsamakIVggbz%2FuQ%2BXwizw5dh90IcY150YR4D3KS8CRFeOoVAyltn0vQ%3D%3D&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Date=20210608T222844Z&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Expires=300&amp;X-Amz-Credential=ASIAQ3PHCVTY2VO2YJ7M%2F20210608%2Fus-east-1%2Fs3%2Faws4_request&amp;X-Amz-Signature=80a64156abbbce5ab112f6a3b75be9883ef7582df8f7638202e65d3da229e5c0&amp;hash=da1ff879087090fb567d65dbca8bbecd58ec71d2ed4509412014174827dacbee&amp;host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61&amp;pii=S0010482521003140&amp;tid=spdf-1f333123-4172-4c36-9af1-93e7bb154805&amp;sid=1c9ce7eb6cace644676be19669d6602a49a8gxrqa&amp;type=client" 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/a0/68/a06843466d07215d7bcc11a58280ae0f259a30a1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.compbiomed.2021.104520"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> elsevier.com </button> </a>

Greedy Bayesian Posterior Approximation with Deep Ensembles [article]

Aleksei Tiulpin, Matthew B. Blaschko
<span title="2021-10-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Ensembles of independently trained neural networks are a state-of-the-art approach to estimate predictive uncertainty in Deep Learning, and can be interpreted as an approximation of the posterior distribution  ...  Subsequently, we consider the problem of ensemble construction, and from the marginal gain of the total objective, we derive a novel diversity term for training ensembles greedily.  ...  We thank CSC -Finnish Center for Science for generous computational resources. We also acknowledge the computational resources provided by the Aalto Science-IT project.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.14275v3">arXiv:2105.14275v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eugfl7pfo5g7pc73xkr5s3n2zu">fatcat:eugfl7pfo5g7pc73xkr5s3n2zu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211015221352/https://arxiv.org/pdf/2105.14275v3.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/43/35/433589fde8db3df39cc6d3ec795dfd503bf5a20f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.14275v3" 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>

Sequential Anomaly Detection using Inverse Reinforcement Learning [article]

Min-hwan Oh, Garud Iyengar
<span title="2020-04-22">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In order to construct a reliable anomaly detection method and take into consideration the confidence of the predicted anomaly score, we adopt a Bayesian approach for IRL.  ...  We use a neural network to represent a reward function. Using a learned reward function, we evaluate whether a new observation from the target agent follows a normal pattern.  ...  C BAYESIAN NEURAL NETWORK In this section, we briefly discuss the work on Bayesian neural network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.10398v1">arXiv:2004.10398v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6tj6b47lkvdm7bw55fsqqizanq">fatcat:6tj6b47lkvdm7bw55fsqqizanq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200502101059/https://arxiv.org/pdf/2004.10398v1.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/2004.10398v1" 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>

Prediction Algorithms: A Study

S. Santha Subbulaxmi, G. Arumugam
<span title="2018-11-05">2018</span> <i title="The Research Publication"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jbqqnwramvckta3km5lxl7n7he" style="color: black;">Asian Journal of Computer Science and Technology</a> </i> &nbsp;
Artificial Neural Network Algorithms Artificial neural network algorithms are inspired by the structure and function of biological neural networks.  ...  A novel [22] hidden naive Bayes (HNB) is proposed with a hidden parent for each attribute. Bayesian Network (BN): Bayesian networks belong to the family of probabilistic graphical model (GMs).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.51983/ajcst-2018.7.3.1896">doi:10.51983/ajcst-2018.7.3.1896</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bteiqgxw2beabb4oe6lmasuyv4">fatcat:bteiqgxw2beabb4oe6lmasuyv4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210825135751/https://www.trp.org.in/wp-content/uploads/2018/11/AJCST-Vol.7-No.3-Oct-Dec-2018-pp.7-12-1.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/52/25/5225e2be49b06a4b701209cbe119787944a5f1a2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.51983/ajcst-2018.7.3.1896"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 3,100 results