Filters








247 Hits in 6.4 sec

Unsupervised Heterophilous Network Embedding via r-Ego Network Discrimination [article]

Zhiqiang Zhong, Guadalupe Gonzalez, Daniele Grattarola, Jun Pang
<span title="2022-03-28">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In addition, it is still an unexplored research question whether existing NE methods adapt well to heterophilous networks.  ...  Specifically, we propose a dual-channel feature embedding mechanism to fuse node attributes and network structure information and leverage a sampling and anonymisation strategy to break the implicit homophily  ...  (a) An example network; (b) Two rooted 2-layers aggregation trees of two connected nodes, i.e., v 0 and v 1 . Duplicated components of two rooted trees are marked with the same shadow colour.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.10866v2">arXiv:2203.10866v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ckdlyfaip5e2polo5xlf3q44oq">fatcat:ckdlyfaip5e2polo5xlf3q44oq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220613050658/https://arxiv.org/pdf/2203.10866v2.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/4a/72/4a722560d4bd42cd040d0e1054be34671ad26411.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.10866v2" 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>

Separability versus Prototypicality in Handwritten Word Retrieval

Jean-Paul van Oosten, Lambert Schomaker
<span title="">2012</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/htymowumwvfj5g7qaexx3w2rti" style="color: black;">2012 International Conference on Frontiers in Handwriting Recognition</a> </i> &nbsp;
An analysis of this problem revealed that two functions needed to be optimised concerning both separability and prototypicality.  ...  Instead of cumbersome SVM training, we present a nearest-centroid method and show that precision improvements of up to 35 percentage points can be achieved, yielding up to 100% precision in data sets with  ...  The support-vector machine training mechanism has an emphasis on separability: the ability to categorise and separate class instances from non-class instances.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icfhr.2012.269">doi:10.1109/icfhr.2012.269</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icfhr/OostenS12.html">dblp:conf/icfhr/OostenS12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qz5x47kbi5gu3pyykvmpbx6qfi">fatcat:qz5x47kbi5gu3pyykvmpbx6qfi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170814080109/http://www.rug.nl/society-business/target/projects-and-rd/publications/separability.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/dd/fe/ddfe0e59e46a3bcf4f73ee8b54e686116b87cd23.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icfhr.2012.269"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [article]

Vijay Badrinarayanan and Alex Kendall and Roberto Cipolla
<span title="2016-10-10">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The upsampled maps are sparse and are then convolved with trainable filters to produce dense feature maps.  ...  SegNet was primarily motivated by scene understanding applications. Hence, it is designed to be efficient both in terms of memory and computational time during inference.  ...  a pixel tolerance distance.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1511.00561v3">arXiv:1511.00561v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m4ct5ahr5rbdrp2vnmklx4byau">fatcat:m4ct5ahr5rbdrp2vnmklx4byau</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191023101443/https://arxiv.org/pdf/1511.00561v3.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/d4/fcd44ab4ebeeb504481350732f21701bf5269fb4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1511.00561v3" 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>

Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering [article]

Fengbin Zhu, Wenqiang Lei, Chao Wang, Jianming Zheng, Soujanya Poria, Tat-Seng Chua
<span title="2021-05-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Open-domain Question Answering (OpenQA) is an important task in Natural Language Processing (NLP), which aims to answer a question in the form of natural language based on large-scale unstructured documents  ...  We then discuss key challenges to developing OpenQA systems and offer an analysis of benchmarks that are commonly used.  ...  ACKNOWLEDGEMENTS This research is supported by the National Research Foundation, Singapore under its International Research Centres in Singapore Funding Initiative and A*STAR under its RIE  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.00774v3">arXiv:2101.00774v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6evkg5cikjdp5fsi3ou3iqqkyq">fatcat:6evkg5cikjdp5fsi3ou3iqqkyq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210517053934/https://arxiv.org/pdf/2101.00774v3.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/29/ea2975c5c77edfdcb6a1a02dc76d009ebdff8056.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.00774v3" 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>

Video-Based Automatic Baby Motion Analysis for Early Neurological Disorder Diagnosis: State of the Art and Future Directions

Marco Leo, Giuseppe Massimo Bernava, Pierluigi Carcagnì, Cosimo Distante
<span title="2022-01-24">2022</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/taedaf6aozg7vitz5dpgkojane" style="color: black;">Sensors</a> </i> &nbsp;
Markerless approaches are easier to set up and maintain (without any human intervention) and they work well on non-collaborative users, making them the most suitable technologies for clinical applications  ...  In the light of clinical findings on early diagnosis of NDD and prompted by recent advances in hardware and software technologies, several researchers tried to introduce automatic systems to analyse the  ...  The IMP consists of 80 items and is applicable to children from 3 to 18 months.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s22030866">doi:10.3390/s22030866</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/35161612">pmid:35161612</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8839211/">pmcid:PMC8839211</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6rv7kiyj35hbrdurqmyfcufnwm">fatcat:6rv7kiyj35hbrdurqmyfcufnwm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220130074648/https://mdpi-res.com/d_attachment/sensors/sensors-22-00866/article_deploy/sensors-22-00866.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/f2/ef/f2ef853fe5d336cd1a4c93f12e813c3429340e9a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s22030866"> <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> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8839211" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

An Overview of Advances of Pattern Recognition Systems in Computer Vision [chapter]

Kidiyo Kpalma, Joseph Ronsi
<span title="2007-06-01">2007</span> <i title="I-Tech Education and Publishing"> Vision Systems: Segmentation and Pattern Recognition </i> &nbsp;
The challenging aim of the system is to use the content-based information to browse an image database and reply to questions like: • "where was I?  ...  One can find the evolution of pattern recognition ; this enables the reader to establish a categorisation of the existing PRSs according to the used methodology and the application.  ...  How to reference In order to correctly reference this scholarly work, feel free to copy and paste the following: Kidiyo Kpalma and Joseph Ronsin (2007) .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5772/4960">doi:10.5772/4960</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pcige6lcefbqtluyuy7xqsaqyu">fatcat:pcige6lcefbqtluyuy7xqsaqyu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190501150942/https://cdn.intechopen.com/pdfs/324.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/86/cd/86cdf72546a219b01353783ab9291539e18c9202.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5772/4960"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications [article]

Yu-Liang Chou and Catarina Moreira and Peter Bruza and Chun Ouyang and Joaquim Jorge
<span title="2021-06-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We performed an LDA topic modelling analysis under a PRISMA framework to find the most relevant literature articles.  ...  This analysis resulted in a novel taxonomy that considers the grounding theories of the surveyed algorithms, together with their underlying properties and applications in real-world data.  ...  An interpretable model, such as linear regression or a decision tree, is able to learn the local importance of each feature.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.04244v2">arXiv:2103.04244v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uqs3y7v7hrhtxkh2ltl4wluyqe">fatcat:uqs3y7v7hrhtxkh2ltl4wluyqe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210328131933/https://arxiv.org/pdf/2103.04244v1.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/60/b5/60b5bfdfe7b83baf1c7040fa7588bb40451ac49c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.04244v2" 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>

The impact of preprocessing on data mining: An evaluation of classifier sensitivity in direct marketing

Sven F. Crone, Stefan Lessmann, Robert Stahlbock
<span title="">2006</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2fqqu5s6wbgk5gcucpt3wqm3gy" style="color: black;">European Journal of Operational Research</a> </i> &nbsp;
towards preprocessing is consequently an important criterion in method evaluation and selection which needs to be considered together with traditional metrics of predictive power and computational efficiency  ...  , neural networks and support vector machines.  ...  Decision trees DT are intuitive methods for classifying a pattern through a sequence of rules or questions, in which the next question depends on the answer on a current question.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.ejor.2005.07.023">doi:10.1016/j.ejor.2005.07.023</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/g7hy2izytja43b25wv4chvbqt4">fatcat:g7hy2izytja43b25wv4chvbqt4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160513063511/http://sven-crone.net/papers/Crone,%20Lessmann,%20Stahlbock%20(2006)%20The%20impact%20of%20preprocessing%20on%20data%20mining%20-%20An%20evaluation%20of%20classifier%20sensitivity%20in%20direct%20marketing%20sdarticle.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/9a/b6/9ab61f85f97899d1e8cff60ee3cbdcfcb85290e8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.ejor.2005.07.023"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Cross-evaluation of a parallel operating SVM – CNN classifier for reliable internal decision-making processes in composite inspection

Sebastian Meister, Mahdieu Wermes, Jan Stüve, Roger M. Groves
<span title="">2021</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wi4npej345ektj44cu3fqi2sgi" style="color: black;">Journal of manufacturing systems</a> </i> &nbsp;
The particular novelty of this study is this intermediate comparison to trace the behaviour of the two classifiers along their image processing chains and to project the results back to the input image  ...  Moreover, the classification score of the SVM as well as the feature vector distances within the SVM are investigated.  ...  This research is part of the project DHiiP-AIR and was financially supported by the Federal Ministry for Economic Affairs and Energy.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jmsy.2021.07.022">doi:10.1016/j.jmsy.2021.07.022</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vpbhdq7rqrczzfabmfuyjhlagq">fatcat:vpbhdq7rqrczzfabmfuyjhlagq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210727081408/https://pdf.sciencedirectassets.com/277340/1-s2.0-S0278612521X00039/1-s2.0-S027861252100159X/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEE8aCXVzLWVhc3QtMSJGMEQCIGN%2FYehSn5W4DBtImA%2B11KMqbUP1VncUAg0ZE6Ldr248AiARwCW9d3Bjm%2FMHXKQJdMBaCVBn64WQX64v7EiRjJNS%2Bir6AwhYEAQaDDA1OTAwMzU0Njg2NSIMuNAvGx9Xqp2bKVFvKtcDnDQRqWUXNCjld7EkHZcNNR5%2FpmGJSu19p%2FI8SXNqgVx06p6Nbf1XGBcrPGWH2PhtJrz919Rf18E7RRSNozgnuuBTVroY%2BCM3GOX3w28V4x0xMlWqQRXbLU1fndZC%2F%2BEf9fFOv%2Fu0O5xx63qhri8XibwiwXuXFPjCxFn7B7a8bzjUX197xGL5C1FDkp57nsG%2FAR%2FjW%2BKxEB8aMb9ZFZOOLMDDiY715NGzkUTh1GKNndy1fM12%2FP%2FUf4LsayA%2FkOQLB%2F%2B0LDKtkw%2BDTD77whQf1WkmoMWH7QLSoMp%2BDkBtSr208AlhScqs3WS2ldBUc%2BXLjOsnOtaX%2B%2BWNhyknxC49lPrCxhX7l%2Bu33S2xVpweKQ1cDVrlzeOvXanGMZE1S8jALt5HI%2Bi1rdHguQJM31wiktO%2FVieh9VBp2czVnsloIrReMMGE2YbL9aueH6klpq2lRt2Z0La2AiedF3Wu4M1AKlz7zKOVfCRLKafHfTe81C%2FgxWFFSkG9WpONyOVXa1vGMuyRqNfQiKiMlavy0RltnO35r%2BySib1kPA%2FDYNIvgIJpha1nLny%2BQT7aqsFdodb5Jm7INY5KtJDGuQV0Kj3L2DAoUi985GQwATjUATBO2OAXS3Ov01v4MLjc%2FocGOqYBeRppicqS3NmXWuJbasLzamLdCZE%2Fon1nZZihVfZb1LamLRDfWJe4gtik4CxSOx8bZqWGpLZT%2FBFjB3VQ%2FxbEOv6FNbu1n6mLTAI%2BEXnaTlGhTQ3NkHBxref7%2BvVGGZjrHKzvLLuCtVyVdwVXy0L%2FLE%2FPneLEix0Pij54sBn2w0oD4cqIN6DCylcMT7%2FUa8R%2FuL%2B3KOVxGj%2B0jGT1J6zTEOAhHeSexg%3D%3D&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Date=20210727T081357Z&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Expires=300&amp;X-Amz-Credential=ASIAQ3PHCVTYWSUC7BEO%2F20210727%2Fus-east-1%2Fs3%2Faws4_request&amp;X-Amz-Signature=72cbdddb20957a06f93a925adf2729d58d6d2f0f83449fca440056c2b1019448&amp;hash=9483d3323e01362888e005d7a87bbaa75b1531785669db704bc35df94a7af242&amp;host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61&amp;pii=S027861252100159X&amp;tid=spdf-3dbe68a7-0425-4791-a2e6-eddcaf30e856&amp;sid=b9cf530893f468418b6b57d6e1b1a11939a5gxrqa&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/7a/ae/7aae57aed91607e4140a83e2d6f1d18df70e6ab5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.jmsy.2021.07.022"> <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>

Exploiting Human Social Cognition for the Detection of Fake and Fraudulent Faces via Memory Networks [article]

Tharindu Fernando, Clinton Fookes, Simon Denman, Sridha Sridharan
<span title="2019-11-17">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Such approaches are seen as a source of disinformation and mistrust, and pose serious concerns to governments around the world.  ...  Experimental results demonstrate the proposed approach achieves superior performance for fake and fraudulent face detection compared to the state-of-the-art.  ...  ACKNOWLEDGMENTS This research was supported by an Australian Research Council (ARC) Discovery grant DP140100793.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.07844v1">arXiv:1911.07844v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h4hhto4byjgbbnaks77slgedca">fatcat:h4hhto4byjgbbnaks77slgedca</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826165313/https://arxiv.org/pdf/1911.07844v1.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/bd/c4/bdc4adb29c8348b3a631ba2c4cad864be4402f6e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.07844v1" 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>

Tree Memory Networks for Modelling Long-term Temporal Dependencies [article]

Tharindu Fernando, Simon Denman, Aaron McFadyen, Sridha Sridharan and Clinton Fookes
<span title="2018-05-20">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a Tree Memory Network (TMN) for modelling long term and short term relationships in sequence-to-sequence mapping problems.  ...  Furthermore, we perform an in depth analysis on the evolution of the memory module content over time and provide visual evidence on how the proposed TMN is able to map both long term and short term relationships  ...  capture both long term and short term relationships via an efficient tree structure.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.04706v2">arXiv:1703.04706v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/as2c3oasdbaljgyy3ohieya6na">fatcat:as2c3oasdbaljgyy3ohieya6na</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200911172807/https://arxiv.org/pdf/1703.04706v2.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/90/90/9090e94124d40b4ddb28d82a222f26dadb02f7cf.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.04706v2" 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>

Separability versus prototypicality in handwritten word-image retrieval

Jean-Paul van Oosten, Lambert Schomaker
<span title="">2014</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jm6w2xclfzguxnhmnmq5omebpi" style="color: black;">Pattern Recognition</a> </i> &nbsp;
The support-vector machine training mechanism has an emphasis on separability: the ability to categorise and separate class instances from non- X?  ...  over a word, is only applicable to a small subset.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patcog.2013.09.006">doi:10.1016/j.patcog.2013.09.006</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4pt3g4fa2nh6pg7gjckikn36ny">fatcat:4pt3g4fa2nh6pg7gjckikn36ny</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180723093712/https://www.rug.nl/research/portal/files/13812524/Separability_versus_Prototypicality_in_Handwritten_Word_image_Retrieval_postprint.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/9f/76/9f7629bec227d5e72456822b2aea71e3f41c4e40.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patcog.2013.09.006"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Darknet Traffic Big-Data Analysis and Network Management to Real-Time Automating the Malicious Intent Detection Process by a Weight Agnostic Neural Networks Framework [article]

Konstantinos Demertzis, Konstantinos Tsiknas, Dimitrios Takezis, Charalabos Skianis, Lazaros Iliadis
<span title="2021-02-16">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
It is an effective and accurate computational intelligent forensics tool for network traffic analysis, the demystification of malware traffic, and encrypted traffic identification in real-time.  ...  Additionally, thanks to the widespread adoption of cloud computing, Device Operators processes, and the Internet of Things, maintaining effective network visibility has become a highly complex and overwhelming  ...  The networks in question created by NAS, although much slower and more complex (Trainable parameters: 98,827), prove to be excellent after training, as evidenced by the results of the table above.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.08411v1">arXiv:2102.08411v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w5ablw4crbbh7anra7kcu5jlay">fatcat:w5ablw4crbbh7anra7kcu5jlay</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210219013912/https://arxiv.org/ftp/arxiv/papers/2102/2102.08411.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/39/25/3925a2230ed5c4c320eb7b0f715e786eb5025bd7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.08411v1" 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>

Hyperbolic Deep Neural Networks: A Survey [article]

Wei Peng, Tuomas Varanka, Abdelrahman Mostafa, Henglin Shi, Guoying Zhao
<span title="2021-02-17">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To stimulate future research, this paper presents acoherent and comprehensive review of the literature around the neural components in the construction of hyperbolic deep neuralnetworks, as well as the  ...  It also presents current applicationsaround various machine learning tasks on several publicly available datasets, together with insightful observations and identifying openquestions and promising future  ...  This work is supported by the Academy of Finland for ICT 2023 project (grant 328115) and project MiGA (grant 316765) and Infotech Oulu.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.04562v3">arXiv:2101.04562v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yqj4zohrqjbplpsdy5f5uglnbu">fatcat:yqj4zohrqjbplpsdy5f5uglnbu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210221070435/https://arxiv.org/pdf/2101.04562v3.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/1f/f8/1ff80e03af01e5fcadeee7ce6970d7620353f171.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.04562v3" 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>

Fusing Interpretable Knowledge of Neural Network Learning Agents For Swarm-Guidance [article]

Duy Tung Nguyen, Kathryn Kasmarik, Hussein Abbass
<span title="2022-04-01">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
where humans and machines need to collaborate on a task, or where there is a requirement to verify the knowledge exchanged between the agents.  ...  Moreover, the framework presents the knowledge learnt by an agent in a human-friendly representation, leading to a better descriptive visual representation of an agent's knowledge.  ...  trainable network and a small weight matrix.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.00272v1">arXiv:2204.00272v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vjld6uugofgexk4og5pyz3w7aq">fatcat:vjld6uugofgexk4og5pyz3w7aq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220518040811/https://arxiv.org/pdf/2204.00272v1.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/1b/30/1b304e5befb450fef04d152e5620ffb0a7f95c69.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.00272v1" 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 247 results