Filters








105 Hits in 4.7 sec

Learning to see people like people [article]

Amanda Song, Linjie Li, Chad Atalla, Garrison Cottrell
<span title="2017-05-05">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Bridging this gap, we develop a method to predict human impressions of faces in 40 subjective social dimensions, using deep representations from state-of-the-art neural networks.  ...  We find that model performance grows as the human consensus on a face trait increases, and that model predictions outperform human groups in correlation with human averages.  ...  End-to-end neural networks were applied to predict facial attractiveness in 2010 [8] (correlation 0.458, face database size=2056, young female faces only).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.04282v1">arXiv:1705.04282v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7pfotjku5necdiwo6n5g5syuai">fatcat:7pfotjku5necdiwo6n5g5syuai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200912093542/https://arxiv.org/pdf/1705.04282v1.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/a5/c8/a5c8fc1ca4f06a344b53dc81ebc6d87f54896722.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.04282v1" 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>

We Know Where We Don't Know: 3D Bayesian CNNs for Credible Geometric Uncertainty [article]

Tyler LaBonte, Carianne Martinez, Scott A. Roberts
<span title="2020-04-02">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Establishing the credibility of these segmentations requires uncertainty quantification (UQ) to identify untrustworthy predictions.  ...  We propose a novel 3D Bayesian convolutional neural network (BCNN), the first deep learning method which generates statistically credible geometric uncertainty maps and scales for application to 3D data  ...  Bayesian Neural Networks (BNNs) Another approach to UQ in deep neural networks is Bayesian learning via variational inference (i.e., a BNN).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.10793v2">arXiv:1910.10793v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yftllyfdune2xgjjhfe6lhafxi">fatcat:yftllyfdune2xgjjhfe6lhafxi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200404000824/https://arxiv.org/pdf/1910.10793v2.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/1910.10793v2" 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>

Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks [article]

Leo Schwinn, René Raab, An Nguyen, Dario Zanca, Bjoern Eskofier
<span title="2021-05-25">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community.  ...  Additionally, we observe that both over- and under-confidence in model predictions result in an inaccurate assessment of model robustness.  ...  Introduction Deep Neural Networks (DNNs) can be easily fooled into making wrong predictions by seemingly negligible perturbations to their input data, called adversarial examples. Szegedy et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.10304v2">arXiv:2105.10304v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gylugnqgcvehjdwjzwfczypopm">fatcat:gylugnqgcvehjdwjzwfczypopm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210529120853/https://arxiv.org/pdf/2105.10304v2.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/41/d0/41d0d2116c2e7de3f65243bf092ba010435293e3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.10304v2" 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>

Machine learning enables long time scale molecular photodynamics simulations [article]

Julia Westermayr, Michael Gastegger, Maximilian F. S. J. Menger, Sebastian Mai, Leticia González, Philipp Marquetand
<span title="2019-07-15">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Instead of expensive quantum chemistry during molecular dynamics simulations, we use deep neural networks to learn the relationship between a molecular geometry and its high-dimensional electronic properties  ...  Photo-induced processes are fundamental in nature, but accurate simulations are seriously limited by the cost of the underlying quantum chemical calculations, hampering their application for long time  ...  Energies and gradients are directly used for training purposes in a single neural network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.09112v2">arXiv:1811.09112v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lymaq2fbcnh4rmo5de55yfn33m">fatcat:lymaq2fbcnh4rmo5de55yfn33m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200828222852/https://arxiv.org/vc/arxiv/papers/1811/1811.09112v1.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/30/d8/30d8cf7b1e34996c093fd9de12dad32e341565d4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.09112v2" 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>

PSD2 Explainable AI Model for Credit Scoring [article]

Neus Llop Torrent
<span title="2021-08-06">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In particular, the project focuses on applying an explainable machine learning model to bank-related databases. The input data were obtained from open data.  ...  The aim of this project is to develop and test advanced analytical methods to improve the prediction accuracy of Credit Risk Models, preserving at the same time the model interpretability.  ...  Acknowledgments We acknowledge financial support by CRIF S.p.A and Università degli Studi di Bologna.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.10367v3">arXiv:2011.10367v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wcfhqfu345blnasarxq3m6rax4">fatcat:wcfhqfu345blnasarxq3m6rax4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201124234916/https://arxiv.org/pdf/2011.10367v1.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/e5/21/e521eb055cbfc3142db74f01b2504b116ec80c8a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.10367v3" 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>

Construction of Optimal Prediction Intervals for Load Forecasting Problems

Abbas Khosravi, Saeid Nahavandi, Doug Creighton
<span title="">2010</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/gnhkf3aieraxhlw7vpy6whnksy" style="color: black;">IEEE Transactions on Power Systems</a> </i> &nbsp;
The delta technique is applied for constructing prediction intervals for outcomes of neural network models.  ...  Simulated annealing is used for minimization of this cost function and adjustment of neural network parameters.  ...  The delta technique is applied for constructing prediction intervals for outcomes of neural network models.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpwrs.2010.2042309">doi:10.1109/tpwrs.2010.2042309</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gmmt6pav4ra4bbs2e5amymr7ai">fatcat:gmmt6pav4ra4bbs2e5amymr7ai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171112135618/https://core.ac.uk/download/pdf/13988460.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/b1/30b14615839a8640ace2d1a6b470dc4611f7d7f9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpwrs.2010.2042309"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Survey of Machine Learning Techniques in Adversarial Image Forensics [article]

Ehsan Nowroozi, Ali Dehghantanha, Reza M. Parizi, Kim-Kwang Raymond Choo
<span title="2020-10-19">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Increasingly, machine learning approaches are also utilized in image forensics.  ...  Image forensic plays a crucial role in both criminal investigations (e.g., dissemination of fake images to spread racial hate or false narratives about specific ethnicity groups) and civil litigation (  ...  For example, a deep neural network may report high confidence in a wrong prediction or can be circumvented by image perturbation techniques.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.09680v1">arXiv:2010.09680v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qzvolq6kvrggfbyg23wrcnykza">fatcat:qzvolq6kvrggfbyg23wrcnykza</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201104214029/https://arxiv.org/pdf/2010.09680v1.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/e2/6b/e26bb73abefe95dcf175dcb6b1dee24efa1b1ee3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.09680v1" 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>

Ensembles of Deep Learning Framework for Stomach Abnormalities Classification

Talha Saeed, Chu Kiong Loo, Muhammad Shahreeza Safiruz Kassim
<span title="">2022</span> <i title="Computers, Materials and Continua (Tech Science Press)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/amujz7fcqna6do727z6ev3ueo4" style="color: black;">Computers Materials &amp; Continua</a> </i> &nbsp;
In several medical imaging tasks, deep learning methods, especially convolutional neural networks (CNNs), have contributed to the stateof-the-art outcomes, where the complicated nonlinear relation between  ...  Hence, Explainable Artificial Intelligence (XAI) techniques are applied to overcome this issue by interpreting the decisions of the CNNs in such wise the physicians can trust.  ...  And estimates of uncertainty can increase the speed of the analysis process because, as opposed to reviewing the whole images for diseases not identified by the CNN, medical professionals may spend their  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.32604/cmc.2022.019076">doi:10.32604/cmc.2022.019076</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cx2qs3rzgrhrlobc47tbd4ovhu">fatcat:cx2qs3rzgrhrlobc47tbd4ovhu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220304101240/https://www.techscience.com/ueditor/files/cmc/TSP_CMC-70-3/TSP_CMC_19076/TSP_CMC_19076.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/2e/71/2e714d1b50d2856a69bc036c47af294b59cb69db.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.32604/cmc.2022.019076"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Software reliability models based on machine learning techniques: A review

Bejjam Vasundhara Devi, R. Kanniga Devi
<span title="">2022</span> <i title="AIP Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3jzz7zp4afbbpdcvegp6zk7rp4" style="color: black;">AIP Conference Proceedings</a> </i> &nbsp;
It compares with the reliability of hardware by reflecting the perfection of architecture and the reliability of hardware.  ...  In order to create outstanding quality, reliable software, the software business has many problems. The reliability of software is important for the reliability of the system.  ...  ., Neural Network Real time control project By NN model for Elman the approach (2008) [34] uses dataset dynamic behavior of the system. Singh et al., (2010) Neural Network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1063/5.0080442">doi:10.1063/5.0080442</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x36ir3y2hjh2pl6nmpfaf3nddu">fatcat:x36ir3y2hjh2pl6nmpfaf3nddu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220504021446/https://aip.scitation.org/doi/pdf/10.1063/5.0080442" 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/25/d5/25d56ef960d4709063f6139652b8cefb5b916acb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1063/5.0080442"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Detection and Mitigation of Rare Subclasses in Deep Neural Network Classifiers [article]

Colin Paterson, Radu Calinescu, Chiara Picardi
<span title="2021-07-07">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose an approach for the detection and mitigation of such rare subclasses in deep neural network classifiers.  ...  In addition we demonstrate how our run-time approach increases the ability of users to identify samples likely to be misclassified at run-time.  ...  This work was funded by the Assuring Autonomy International Programme, and the UKRI project EP/V026747/1 'Trustworthy Autonomous Systems Node in Resilience'.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.12780v2">arXiv:1911.12780v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/t2hj5bzny5fwjlajeek2jyyfem">fatcat:t2hj5bzny5fwjlajeek2jyyfem</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210712070913/https://arxiv.org/pdf/1911.12780v2.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/b5/47/b54765a227100a3259c42ed0225950aaf3295031.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.12780v2" 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 on Machine Learning-Based Performance Improvement of Wireless Networks: PHY, MAC and Network Layer

Merima Kulin, Tarik Kazaz, Eli De Poorter, Ingrid Moerman
<span title="2021-01-29">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ikdpfme5h5egvnwtvvtjrnntyy" style="color: black;">Electronics</a> </i> &nbsp;
We first categorize these works into: radio analysis, MAC analysis and network prediction approaches, followed by subcategories within each.  ...  all layers of the protocol stack: PHY, MAC and network.  ...  (MAC) analysisNetwork prediction Furthermore, within each of the above categories, we identified several classes of research approaches illustrated in Figure 16 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics10030318">doi:10.3390/electronics10030318</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p6jslz26dvfvbpnqzmrpptloim">fatcat:p6jslz26dvfvbpnqzmrpptloim</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210715101120/https://repository.tudelft.nl/islandora/object/uuid%3A7cbdb3ce-34e9-48aa-b84d-483a1a2d27c7/datastream/OBJ/download" 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/83/ef/83ef0ae64c11b42ecbe8d307efd4e5c317763afb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics10030318"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Car Pose in Context: Accurate Pose Estimation with Ground Plane Constraints [article]

Pengfei Li, Weichao Qiu, Michael Peven, Gregory D. Hager, Alan L. Yuille
<span title="2019-12-09">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we describe a method for estimating the pose of cars in a scene jointly with the ground plane that supports them.  ...  We also show that introducing the planar constraint allows us to estimate camera focal length in a reliable manner.  ...  Acknowledgements Supported by the Intelligence Advanced Research Projects Activity (IARPA) via Depart-ment of Interior/ Interior Business Center (DOI/IBC) contract number D17PC00342. The U.S.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.04363v1">arXiv:1912.04363v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vvbh75vpkfe6fk535n6vetqrje">fatcat:vvbh75vpkfe6fk535n6vetqrje</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825200641/https://arxiv.org/pdf/1912.04363v1.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/3e/c5/3ec5d2fcf2b070401f1178326b66ab0f0c0059b1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.04363v1" 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>

EPGAT: Gene Essentiality Prediction With Graph Attention Networks [article]

João Schapke, Anderson Tavares, Mariana Recamonde-Mendoza
<span title="2020-07-19">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Given these limitations, we proposed EPGAT, an approach for essentiality prediction based on Graph Attention Networks (GATs), which are attention-based Graph Neural Networks (GNNs) that operate on graph-structured  ...  interaction (PPI) networks, to predict essential genes.  ...  For the analysis of topology-based methods, genes in the testing set were ordered by their centrality measure in a descending order and the resulting rank was used for AUC score analysis.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.09671v1">arXiv:2007.09671v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/i2p6p2nguzfgfjiwofjgijdcam">fatcat:i2p6p2nguzfgfjiwofjgijdcam</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826060523/https://arxiv.org/pdf/2007.09671v1.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/a2/89/a289cf5bfa97590bc2f15500701fbbd22b6f888f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.09671v1" 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>

Simulation of Human Ear Recognition Sound Direction Based on Convolutional Neural Network

Zhuhe Wang, Nan Li, Tao Wu, Haoxuan Zhang, Tao Feng
<span title="2020-07-14">2020</span> <i title="Walter de Gruyter GmbH"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fvcuwwb4brauziwelchs6y6lzi" style="color: black;">Journal of Intelligent Systems</a> </i> &nbsp;
AbstractIn recent years, more and more people are applying Convolutional Neural Networks to the study of sound signals.  ...  However, we use the original data of the two channels as the input of the convolutional neural network, and the resolution effect can reach more than 0.9.  ...  Simulation of Human Ear Recognition Sound Direction Based on Convolutional Neural Network  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1515/jisys-2019-0250">doi:10.1515/jisys-2019-0250</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qglwxuvnibfttpp5dnnbtogtsi">fatcat:qglwxuvnibfttpp5dnnbtogtsi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200715052156/https://www.degruyter.com/downloadpdf/journals/jisys/30/1/article-p209.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/2e/e5/2ee5027ee4862a9e5bf12268a7e167f4dd24ff09.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1515/jisys-2019-0250"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> degruyter.com </button> </a>

TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems [article]

Wenbo Guo, Lun Wang, Xinyu Xing, Min Du, Dawn Song
<span title="2019-08-08">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A trojan backdoor is a hidden pattern typically implanted in a deep neural network.  ...  As such, given a deep neural network model and clean input samples, it is very challenging to inspect and determine the existence of a trojan backdoor.  ...  Different from the Vanilla gradient decent, which has a fixed learning rate, Adam adjusts the learning rate via dividing it by an exponentially decaying average of squared gradients.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.01763v2">arXiv:1908.01763v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/iuf5fn56wveebixixy64r52eee">fatcat:iuf5fn56wveebixixy64r52eee</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200903152739/https://arxiv.org/pdf/1908.01763v1.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/ec/05/ec055a8c66595e70210cf257a7dd7cf9d4f6a006.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.01763v2" 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 105 results