Filters








374,136 Hits in 8.2 sec

The multi-source model for dimensioning data networks

T. Bonald, C. Comte
<span title="">2016</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/blfmvfslmbggxhopuigjdb3jma" style="color: black;">Computer Networks</a> </i> &nbsp;
Traffic modeling is key to the dimensioning of data networks.  ...  We qualify this model as multi-source since each user now behaves as an independent traffic source.  ...  In fact, the flow-level models of data networks can be considered as the analogues for the Erlang model of telephone networks and its extensions to multi-rate circuit-switched networks [5] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.comnet.2016.03.019">doi:10.1016/j.comnet.2016.03.019</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/epydoxe6xzgwhdawnamp646pcu">fatcat:epydoxe6xzgwhdawnamp646pcu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829112624/https://hal.archives-ouvertes.fr/hal-01314992/document" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e3/a2/e3a2cee124b720ae9f71fb0cbdbaafac095bf6f3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.comnet.2016.03.019"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Multi-path Routing for Mesh/Torus-Based NoCs

Yaoting Jiao, Yulu Yang, Ming He, Mei Yang, Yingtao Jiang
<span title="">2007</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q4htbe6iofd7zjlr6cgteixwfq" style="color: black;">Fourth International Conference on Information Technology (ITNG&#39;07)</a> </i> &nbsp;
For the proposed multi-path routing scheme, we consider two transport models: the multi-path full bitbank transport model and the multi-path half bitbank transport model.  ...  In this paper, we propose a multi-path routing scheme to maximize the data throughput by utilizing multiple paths for concurrent data transmission.  ...  Section 2 describes the two transport models. Section 3 presents the multi-path routing scheme. Section 4 is focused on the proof of the blocking avoidance with single source node in the network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/itng.2007.129">doi:10.1109/itng.2007.129</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/itng/JiaoYHYJ07.html">dblp:conf/itng/JiaoYHYJ07</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sizpv7a4kzcn5os3xy2uqck6aa">fatcat:sizpv7a4kzcn5os3xy2uqck6aa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20080221171011/http://www.ee.unlv.edu/~meiyang/publications/yang_multipath.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/2c/82/2c82cc2ed48aaf73a52057cdfb4432feec28f7a3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/itng.2007.129"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Urban Multi-Source Spatio-Temporal Data Analysis Aware Knowledge Graph Embedding

Ling Zhao, Hanhan Deng, Linyao Qiu, Sumin Li, Zhixiang Hou, Hai Sun, Yun Chen
<span title="2020-02-01">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/nzoj5rayr5hutlurimhzyjlory" style="color: black;">Symmetry</a> </i> &nbsp;
To explore the network structure and semantic relationships, we propose a general framework for multi-source spatio-temporal data analysis via knowledge graph embedding.  ...  The framework extracts low-dimensional feature representation from multi-source spatio-temporal data in a high-dimensional space, and recognizes the network structure and semantic relationships about multi-source  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/sym12020199">doi:10.3390/sym12020199</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r4r5vpe57feg5mlyjv6f3awriq">fatcat:r4r5vpe57feg5mlyjv6f3awriq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200210195506/https://res.mdpi.com/d_attachment/symmetry/symmetry-12-00199/article_deploy/symmetry-12-00199.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/af/23/af232246850ed9cfdaa59799f92ae85d34979c31.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/sym12020199"> <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>

Multi-encoder Transformer Network for Automatic Post-Editing

Jaehun Shin, Jong-Hyeok Lee
<span title="">2018</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ofil6chs6zhkndqe6tcritiiwm" style="color: black;">Proceedings of the Third Conference on Machine Translation: Shared Task Papers</a> </i> &nbsp;
This paper describes the POSTECH's submission to the WMT 2018 shared task on Automatic Post-Editing (APE). We propose a new neural end-to-end post-editing model based on the transformer network.  ...  We modified the encoder-decoder attention to reflect the relation between the machine translation output, the source and the postedited translation in APE problem.  ...  Acknowledgments This work was supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (R7119-16-1001, Core technology development  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w18-6470">doi:10.18653/v1/w18-6470</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wmt/ShinL18.html">dblp:conf/wmt/ShinL18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tr42uskbxzfszhly2zaoux65ja">fatcat:tr42uskbxzfszhly2zaoux65ja</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200508051419/https://www.aclweb.org/anthology/W18-6470.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/a2/3ea2c8bd1ff77d9a0398c86bc6aef57a1320696d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w18-6470"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Multi-source data processing and fusion method for power distribution internet of things based on edge intelligence [article]

Quande Yuan, Yuzhen Pi, Lei Kou, Fangfang Zhang, Yang Li, Zhenming Zhang
<span title="2022-03-30">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
By introducing the Box-Cox transform to improve the data offset problem in the Zscore normalization process, a multi-source heterogeneous data processing method for distribution networks based on the Box-Cox  ...  A multi-source data fusion model based on DS inference with conflict optimization is constructed to ensure the effective fusion of distribution data sources from different domains.  ...  Section 4 provides the process for building a multi-source data fusion model for the power distribution network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.17230v1">arXiv:2203.17230v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fwrb46t775anvnh76b7wssvixe">fatcat:fwrb46t775anvnh76b7wssvixe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220617133415/https://arxiv.org/ftp/arxiv/papers/2203/2203.17230.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/30/6d/306d41d01090557ea90bbf1751e886552c4fbaa2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.17230v1" 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>

Deadlock-Free Multi-Path Routing for Torus-Based NoCs

Yaoting Jiao, Mei Yang, Yingtao Jiang, Yulu Yang, Xiaochun Yun
<span title="">2008</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q4htbe6iofd7zjlr6cgteixwfq" style="color: black;">Fifth International Conference on Information Technology: New Generations (itng 2008)</a> </i> &nbsp;
In our previous work, a Multi-Path Routing (MPR) scheme was proposed to maximize the data throughput for torus-based NoCs by utilizing multiple paths for concurrent data transmission.  ...  In this virtual channel model, every physical channel on the network is split into about 3.5 virtual channels on average.  ...  For single-source situation, the analysis of data throughput is same as in [9] , which is omitted here. For multi-source situations, there may exist blockings in the network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/itng.2008.171">doi:10.1109/itng.2008.171</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/itng/JiaoYJYY08.html">dblp:conf/itng/JiaoYJYY08</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yjpkycfyjfec7bkbzwfsqhjxcm">fatcat:yjpkycfyjfec7bkbzwfsqhjxcm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20100624051628/http://www.ee.unlv.edu/~meiyang/publications/ITNG08-jiao.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/0c/52/0c5277a1cc4f467fe48dd6ada01ec08b1261c19c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/itng.2008.171"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A MDA-based campus data analysis and visualization framework

Jiangning Xie, Xueqing Li, Lei Wang, Yuzhen Niu
<span title="2012-10-29">2012</span> <i title="MECS Publisher"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/m7t4p2keq5h2rgbfjgwqthgp4q" style="color: black;">International Journal of Education and Management Engineering</a> </i> &nbsp;
The framework is composed of multi-dimension data modeling, data extraction, visualization-based data exhibition, and some other modules.  ...  Data extraction solves the problem caused by separately stored data and heterogeneous data. Multi-dimension data modeling analysis and visualization enhances the analysis ability of existing system.  ...  Data Acquisition For a specific business analysis topic, after completing the multi-dimension data modeling, we extract the data for analysis and visualization from different data sources.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5815/ijeme.2012.10.11">doi:10.5815/ijeme.2012.10.11</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wp7oezhfs5eljbfsj3jj5dba74">fatcat:wp7oezhfs5eljbfsj3jj5dba74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809103649/http://www.mecs-press.org/ijeme/ijeme-v2-n10/IJEME-V2-N10-11.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/9c/69/9c690d90772ce05bd5a9a770de50479458319a75.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5815/ijeme.2012.10.11"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Data Science Approach for a Cross-disciplinary Understanding of Urban Phenomena: Application to Energy Efficiency of Buildings

Servigne Sylvie, Yann Gripay, Deleuil Jean-Michel, Nguyen Céline, Jay Jacques, Cavadenti Olivier, Mebrouk Radouane
<span title="">2015</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5i4djr4tgnbobnjegejzpw7nny" style="color: black;">Procedia Engineering</a> </i> &nbsp;
We focus on a generic model for data acquisition campaigns based on the concept of generic sensor.  ...  Our goal is to develop theoretical and practical tools to model, explore and exploit heterogeneous data from various sources in order to understand a phenomenon.  ...  Acknowledgment This work was supported by the LABEX IMU (ANR-10-LABX-0088) of University of Lyon, within the program "Investissements d'Avenir" (ANR-11-IDEX-0007) operated by the French National Research  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.proeng.2015.07.353">doi:10.1016/j.proeng.2015.07.353</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/okcbgb2ycrhhdge7z4bi2r554i">fatcat:okcbgb2ycrhhdge7z4bi2r554i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170923222603/http://publisher-connector.core.ac.uk/resourcesync/data/elsevier/pdf/089/aHR0cDovL2FwaS5lbHNldmllci5jb20vY29udGVudC9hcnRpY2xlL3BpaS9zMTg3NzcwNTgxNTAxNjM2Nw%3D%3D.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/c3/fc/c3fc3aa641b301501c5c39366fcf52783ea868fd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.proeng.2015.07.353"> <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>

Dimensioning of multi-granular optical networks

M. De Leenheer, C. Develder, B. Dhoedt, P. Demeester
<span title="">2008</span> <i title="IEEE"> 2008 34th European Conference on Optical Communication </i> &nbsp;
We present an ILP model for dimensioning optical networks that support wavelength and sub-wavelength switching.  ...  Results indicate significant reductions in cost and node-complexity with such multi-granular networks.  ...  To this end, we propose a dimensioning algorithm to optimally install switching ports in the network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ecoc.2008.4729521">doi:10.1109/ecoc.2008.4729521</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wwvbl3kfcnhhhmbrizhfcf53jq">fatcat:wwvbl3kfcnhhhmbrizhfcf53jq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809140352/http://users.atlantis.ugent.be/cdvelder/papers/2008/deleenheer2008ecoc.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/e0/58/e0587e1f02ad005aa5c64604aa7693ec94cf186c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ecoc.2008.4729521"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

I Know Where You Are Coming From: On the Impact of Social Media Sources on AI Model Performance (Student Abstract)

Yang Qi, Farseev Aleksandr, Filchenkov Andrey
<span title="2020-04-03">2020</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
Specifically, in this work, we will study the performance of different machine learning models when being learned on multi-modal data from different social networks.  ...  Particularly, the literature on modeling multi-modal data from multiple social networks is relatively sparse, which had inspired us to take a deeper dive into the topic in this preliminary study.  ...  Acknowledgments This research was funded by the Government of Russian Federation, Grant 08-08.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i10.7258">doi:10.1609/aaai.v34i10.7258</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lkuylcgl6rdajjebtqn5phrgxy">fatcat:lkuylcgl6rdajjebtqn5phrgxy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201103214849/https://aaai.org/ojs/index.php/AAAI/article/download/7258/7112" 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/4b/15/4b1592d632cb9f78f1260c882d0547b27c6ec5bf.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i10.7258"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

I Know Where You Are Coming From: On the Impact of Social Media Sources on AI Model Performance [article]

Qi Yang, Aleksandr Farseev, Andrey Filchenkov
<span title="2020-02-05">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Specifically, in this work, we will study the performance of different machine learning models when being learned on multi-modal data from different social networks.  ...  Particularly, the literature on modeling multi-modal data from multiple social networks is relatively sparse, which had inspired us to take a deeper dive into the topic in this preliminary study.  ...  Acknowledgments This research was funded by the Government of Russian Federation, Grant 08-08.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.01726v1">arXiv:2002.01726v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hhskgffi5nazrfiddwlq7f4xei">fatcat:hhskgffi5nazrfiddwlq7f4xei</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200322042644/https://arxiv.org/pdf/2002.01726v1.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/2002.01726v1" 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>

Style Transfer in Text: Exploration and Evaluation [article]

Zhenxin Fu, Xiaoye Tan, Nanyun Peng, Dongyan Zhao, Rui Yan
<span title="2017-11-27">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We explore two models to achieve this goal, and the key idea behind the proposed models is to learn separate content representations and style representations using adversarial networks.  ...  However, the progress in language style transfer is lagged behind other domains, such as computer vision, mainly because of the lack of parallel data and principle evaluation metrics.  ...  Acknowledgment We thank Jin-ge Yao for discussions on this paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.06861v2">arXiv:1711.06861v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hna3yquv7rhsdlogsxbkum773y">fatcat:hna3yquv7rhsdlogsxbkum773y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191015142615/https://arxiv.org/pdf/1711.06861v2.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/09/d7/09d74c7bec923ff697f9d1ec4933aea0198ee544.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1711.06861v2" 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>

Seismic Inversion by Multi-dimensional Newtonian Machine [article]

Yuqing Chen, Erdinc Saygin
<span title="2021-12-16">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Newtonian machine learning (NML) is a wave-equation inversion method that inverts single-dimensional latent space (LS) features of the seismic data for retrieving the subsurface background velocity model  ...  Because its LS feature dimension is too small to preserve the dynamic information, such as the waveform variations, of the seismic data.  ...  Here, k indicates the dimension index of the multi-dimensional LS feature. For simplicity, we assume the LS feature dimension equals two.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.08629v1">arXiv:2112.08629v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/435esilwpngtthzmsjnuxv2zfq">fatcat:435esilwpngtthzmsjnuxv2zfq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211224073751/https://arxiv.org/pdf/2112.08629v1.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/cb/2f/cb2f1ffb5ed310dc49066e6e6529c90f913050c5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.08629v1" 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>

Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism [article]

Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker
<span title="2021-02-07">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
data show that the proposed system improves by 9% relative the source separation performance over a strong multi-channel baseline, and it increases the speech recognition accuracy by more than 16% relative  ...  To efficiently inform the speaker information to the extraction model, we propose a new speaker conditioning mechanism by designing an additional speaker branch for receiving external speaker embeddings  ...  Speech extraction network The multi-channel separation network in [12] trained with PIT has been set as the baseline for comparison.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.03762v1">arXiv:2102.03762v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w2k7tt7zo5cgdkonh5az4wx36y">fatcat:w2k7tt7zo5cgdkonh5az4wx36y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210211131147/https://arxiv.org/pdf/2102.03762v1.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/91/ef/91efb41cd0ad008f100aa4401650566dd3b26056.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.03762v1" 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>

Improving sentence simplification model with ordered neurons network

Chunhui Deng, Lemin Zhang, Huifang Deng
<span title="2021-05-15">2021</span> <i title="Institution of Engineering and Technology (IET)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/l2p2a7zjnreudkkctzwtgdzigi" style="color: black;">CAAI Transactions on Intelligence Technology</a> </i> &nbsp;
In this model, an ordered neurons network is introduced and can provide sentence-level structural information for the encoder and decoder.  ...  The problem can be addressed with an ON-MULTI-STAGE model constructed based on the improved MULTI-STAGE encoder model.  ...  To the best of our knowledge, the ON-MULTI-STAGE model is the first Seq2Seq model to use ON networks and the first model to use the ON network for sentence simplification.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1049/cit2.12047">doi:10.1049/cit2.12047</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zssrhrncnvf2hfy7mvo35w5ca4">fatcat:zssrhrncnvf2hfy7mvo35w5ca4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210716222816/https://ietresearch.onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cit2.12047" 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/8b/df/8bdf268f76169421140e2926afe2084abb501dc9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1049/cit2.12047"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 374,136 results