Filters








295,198 Hits in 3.7 sec

Angle-based Search Space Shrinking for Neural Architecture Search [article]

Yiming Hu, Yuding Liang, Zichao Guo, Ruosi Wan, Xiangyu Zhang, Yichen Wei, Qingyi Gu, Jian Sun
<span title="2020-07-16">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In particular, we propose an angle-based metric to guide the shrinking process.  ...  We provide comprehensive evidences showing that, in weight-sharing supernet, the proposed metric is more stable and accurate than accuracy-based and magnitude-based metrics to predict the capability of  ...  In this section, we further investigate convergence behaviors of angle-based metric and accuracy-based metric in supernet training.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.13431v3">arXiv:2004.13431v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mgsw5qgnmzco3hcxre2flyyowm">fatcat:mgsw5qgnmzco3hcxre2flyyowm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200723153346/https://arxiv.org/pdf/2004.13431v3.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/b2/df/b2df0029708a8a897428a3b7b2c03e32b4222c04.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.13431v3" 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>

Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces [article]

Bert Moons, Parham Noorzad, Andrii Skliar, Giovanni Mariani, Dushyant Mehta, Chris Lott, Tijmen Blankevoort
<span title="2021-08-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
DONNA consists of three phases. First, an accuracy predictor is built using blockwise knowledge distillation from a reference model.  ...  Third, optimal models are quickly finetuned to training-from-scratch accuracy. DONNA is up to 100x faster than MNasNet in finding state-of-the-art architectures on-device.  ...  A.4.2 Choice of Quality Metrics Apart from using the Noise-To-Signal-Power-Ratio (NSR) (See Section 3), other quality metrics can be extracted and used in an accuracy predictor as well.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.08859v3">arXiv:2012.08859v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x5oamrnlb5a7dn6rmfappwgima">fatcat:x5oamrnlb5a7dn6rmfappwgima</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210901073811/https://arxiv.org/pdf/2012.08859v3.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/ec/ad/ecad155ff717352c483b366b7722066c409f398f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.08859v3" 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>

Searching for Robust Neural Architectures via Comprehensive and Reliable Evaluation [article]

Jialiang Sun, Tingsong Jiang, Chao Li, Weien Zhou, Xiaoya Zhang, Wen Yao, Xiaoqian Chen
<span title="2022-03-07">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In addition, existing methods taking adversarial noise as the evaluation just use the robust accuracy of the FGSM or PGD, but these adversarial attacks could not provide the adequately reliable evaluation  ...  Also, among the adversarial noise, we use the composite adversarial attack obtained by random search as the new metric to evaluate the robustness of the model architectures.  ...  also an improvement of about 7% in the natural noise.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.03128v1">arXiv:2203.03128v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/g3bva6i2ozemnjnk6nazzrcpwi">fatcat:g3bva6i2ozemnjnk6nazzrcpwi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220309095929/https://arxiv.org/pdf/2203.03128v1.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/67/9f/679f8bdd565a2535fb5e4c01dfa49d59449a2a47.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.03128v1" 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>

Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training? [article]

Jisoo Mok, Byunggook Na, Ji-Hoon Kim, Dongyoon Han, Sungroh Yoon
<span title="2022-03-28">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
With minimal amount of training, LGA obtains a meaningful level of rank correlation with the post-training test accuracy of an architecture.  ...  In Neural Architecture Search (NAS), reducing the cost of architecture evaluation remains one of the most crucial challenges.  ...  Metrics Summary In Table A1 , we provide an overview of the NTK-based metrics studied in the main paper, along with the direction of their rank correlation with the final test accuracy of a neural architecture  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.14577v1">arXiv:2203.14577v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/il6cxrdcjzbd3ig7hxuqzohe2a">fatcat:il6cxrdcjzbd3ig7hxuqzohe2a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220523215742/https://arxiv.org/pdf/2203.14577v1.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/c3/50/c3508692fd8580af338898354e7d7f71c4163d9b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.14577v1" 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>

End-to-end speech recognition accuracy metric for voice-search tasks

Michael Levit, Shuangyu Chang, Bruce Buntschuh, Nick Kibre
<span title="">2012</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rc5jnc4ldvhs3dswicq5wk3vsq" style="color: black;">2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</a> </i> &nbsp;
We introduce a novel metric for speech recognition success in voice search tasks, designed to reflect the impact of speech recognition errors on user's overall experience with the system.  ...  The results show that search-based recognition accuracy is significantly higher than accuracy based on sentence error rate computation, and that the automated system is very successful in replicating human  ...  In the remainder of this paper we describe our approach to a search-based speech recognition accuracy metric that is based on human intuition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icassp.2012.6289078">doi:10.1109/icassp.2012.6289078</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icassp/LevitCBK12.html">dblp:conf/icassp/LevitCBK12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qfurnjujzzhlthrgqdndad7fd4">fatcat:qfurnjujzzhlthrgqdndad7fd4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809160804/http://mirlab.org/conference_papers/International_Conference/ICASSP%202012/pdfs/0005141.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/c8/33/c833e0fa5cd8164d3e68e90ce4cbc6e208f13b11.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icassp.2012.6289078"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Bandit-Based Algorithm for Fairness-Aware Hyperparameter Optimization [article]

André F. Cruz, Pedro Saleiro, Catarina Belém, Carlos Soares, Pedro Bizarro
<span title="2020-10-22">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In practice, an exhaustive search over all possible techniques and hyperparameters is needed to find optimal fairness-accuracy trade-offs.  ...  Furthermore, without extra training cost, it consistently finds configurations attaining substantially improved fairness at a comparatively small decrease in predictive accuracy.  ...  For the FB-auto variant of Fairband, aiming for an automated balance between both metrics, we employ the same strategy for setting α as that used during search.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.03665v2">arXiv:2010.03665v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ryhu63ugifeejjpwnbm3dzo7zu">fatcat:ryhu63ugifeejjpwnbm3dzo7zu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201018141157/https://arxiv.org/pdf/2010.03665v1.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> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.03665v2" 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>

CONetV2: Efficient Auto-Channel Size Optimization for CNNs [article]

Yi Ru Wang, Samir Khaki, Weihang Zheng, Mahdi S. Hosseini, Konstantinos N. Plataniotis
<span title="2021-10-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Further, since the standard performance indicators (accuracy, loss) fail to capture the performance of individual network components (providing an overall network evaluation), we introduce a novel metric  ...  Combining dependency extraction, metrics, and knowledge distillation, we introduce an efficient searching algorithm, with simulated annealing inspired stochasticity, and demonstrate its effectiveness in  ...  Upon stabilizing, the metrics for most layers exhibit an upwards trend until reaching a plateau in the later search trials. Fig. 11 . Metric Evolution of Simulated Annealing.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.06830v1">arXiv:2110.06830v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/frn4xbuuubd73dqj37h3sz4bzm">fatcat:frn4xbuuubd73dqj37h3sz4bzm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211016210147/https://arxiv.org/pdf/2110.06830v1.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/c4/a6/c4a6729a8010a33c0d94b46635891090577cfa37.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.06830v1" 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>

Fast Similarity Search for Learned Metrics

B. Kulis, P. Jain, K. Grauman
<span title="">2009</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3px634ph3vhrtmtuip6xznraqi" style="color: black;">IEEE Transactions on Pattern Analysis and Machine Intelligence</a> </i> &nbsp;
Given a collection of examples, we learn a Mahalanobis distance using an information-theoretic metric learning technique that adapts prior knowledge about pairwise distances to incorporate similarity and  ...  We propose a method to efficiently index into a large database of examples according to a learned metric.  ...  When searching only 5% of the database, our learned hash functions suffer no loss in accuracy yet enable an average 13x speedup (maximum speedup 34x) relative to an exhaustive scan with the learned metric  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2009.151">doi:10.1109/tpami.2009.151</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/19834137">pmid:19834137</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hxm7popjxzfj3gpukzn43jufau">fatcat:hxm7popjxzfj3gpukzn43jufau</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20130531202935/http://www.cs.utexas.edu:80/~pjain/pubs/hashing_tr.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/82/5a/825a6921537d3fa2c60263989e9b630b8c8887c6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2009.151"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Controller placement methods analysis

Joseph Hollinghurst, Ayalvadi Ganesh, Timothy Bauge
<span title="">2016</span> <i title="IEEE"> 2016 6th International Conference on Information Communication and Management (ICICM) </i> &nbsp;
Further Accuracy Tests In order to test the accuracy of the algorithms further a sample of topologies from the internet topology zoo was used [14] .  ...  Full Search Method The full search method looks at every possibility of clusters available. The metrics and corresponding clusters are then kept in memory and searched to find the minimum.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/infocoman.2016.7784250">doi:10.1109/infocoman.2016.7784250</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dwbqzmrpzje7dpcwkej3ks6w34">fatcat:dwbqzmrpzje7dpcwkej3ks6w34</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180719042747/https://research-information.bristol.ac.uk/files/95966929/Controller_Placement_Methods_Analysis_J_Hollinghurst.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/a7/00/a700b4f23f0b145cdd3ae73c3d389be2ec7f20fc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/infocoman.2016.7784250"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Efficient Neural Network Compression [article]

Hyeji Kim, Muhammad Umar Karim Khan, Chong-Min Kyung
<span title="2019-04-12">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose an efficient method for obtaining the rank configuration of the whole network.  ...  We propose novel accuracy metrics to represent the accuracy and complexity relationship for a given neural network.  ...  This layer-wise accuracy metrics can be used to predict the contribution of an individual layer to the overall accuracy of the network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.12781v3">arXiv:1811.12781v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pn43ecujbrcyjfgpgoi6yskwde">fatcat:pn43ecujbrcyjfgpgoi6yskwde</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928215455/https://arxiv.org/pdf/1811.12781v3.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/ad/09ad67fd3dce491782fff083758e836b601a4cd8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.12781v3" 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>

Managing performance vs. accuracy trade-offs with loop perforation

Stelios Sidiroglou-Douskos, Sasa Misailovic, Henry Hoffmann, Martin Rinard
<span title="">2011</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dj7g645z6zfl5lut4iwy5walyu" style="color: black;">Proceedings of the 19th ACM SIGSOFT symposium and the 13th European conference on Foundations of software engineering - SIGSOFT/FSE &#39;11</a> </i> &nbsp;
These variants occupy different points in the underlying performance vs. accuracy tradeoff space.  ...  ) accuracy losses.  ...  The perforated computation skips some of the items, returning one of the items from the remaining part of the search space. • Search Metric: The application uses a search metric to drive a search for the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2025113.2025133">doi:10.1145/2025113.2025133</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sigsoft/Sidiroglou-DouskosMHR11.html">dblp:conf/sigsoft/Sidiroglou-DouskosMHR11</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dafr6sxbp5c3bovx5ho52cqeoa">fatcat:dafr6sxbp5c3bovx5ho52cqeoa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180724163131/http://dspace.mit.edu/bitstream/handle/1721.1/72440/Rinard_Managing%20performance.pdf;jsessionid=D0D15CBDB3A7B75B59BF8ADC12C02386?sequence=1" 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/21/9b/219b47356dcd3c02a04837be9be7ae072153a9d1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2025113.2025133"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Fast image search for learned metrics

Prateek Jain, Brian Kulis, Kristen Grauman
<span title="">2008</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2008 IEEE Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
We introduce a method that enables scalable image search for learned metrics.  ...  Our learned metrics improve accuracy relative to commonly-used metric baselines, while our hashing construction enables efficient indexing with learned distances and very large databases. 978-1-4244-2243  ...  This research was supported in part by grants from ORAU and Microsoft Research.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2008.4587841">doi:10.1109/cvpr.2008.4587841</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/JainKG08.html">dblp:conf/cvpr/JainKG08</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qf7rlbtyxff4fkvltt33cnz46i">fatcat:qf7rlbtyxff4fkvltt33cnz46i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809213638/http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_CVPR_2008/data/papers/501.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/11/e7/11e7d074e4deebfed771d0aa226f4160f4c5c82b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2008.4587841"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

MIMHD: Accurate and Efficient Hyperdimensional Inference Using Multi-Bit In-Memory Computing [article]

Arman Kazemi, Mohammad Mehdi Sharifi, Zhuowen Zou, Michael Niemier, X. Sharon Hu, Mohsen Imani
<span title="2021-06-22">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In-memory computing implementations of HDC are desirable since they can significantly reduce data transfer overheads.  ...  However, utilizing multi-bit HVs allows HDC to achieve acceptable accuracies in lower dimensions which in turn leads to higher energy efficiencies.  ...  ACKNOWLEDGMENT This work was supported in part by Semiconductor Research Corporation (SRC) Task No. 2988.001, ASCENT, Department of the Navy, Office of Naval Research, grant #N00014-21-1-2225, and a generous  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.12029v1">arXiv:2106.12029v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/npmwowsm2zhzpe24ue63crhucm">fatcat:npmwowsm2zhzpe24ue63crhucm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210625210129/https://arxiv.org/pdf/2106.12029v1.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/8b/d6/8bd63a8c9e27e9f61744833360f04c0d11a62aaa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.12029v1" 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>

Approximate Similarity Search in Genomic Sequence Databases Using Landmark-Guided Embedding

Ahmet Sacan, I. Hakki Toroslu
<span title="">2008</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rnsf6ip73jbf5giprd5odf3nvm" style="color: black;">First International Workshop on Similarity Search and Applications (sisap 2008)</a> </i> &nbsp;
The approximate representation is shown to provide several orders of magnitude speed-up in similarity search compared to the exact representation, while maintaining comparable search accuracy.  ...  Similarity search in sequence databases is of paramount importance in bioinformatics research.  ...  We would also like thank the anonymous reviewers for their critical analysis of and corrections to the manuscript.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/sisap.2008.7">doi:10.1109/sisap.2008.7</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sisap/SacanT08.html">dblp:conf/sisap/SacanT08</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7ugcpjegojg3rh4irqgmxuy22q">fatcat:7ugcpjegojg3rh4irqgmxuy22q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20081031173716/http://www.ceng.metu.edu.tr/~ahmet/Wiki/_media/papers/2008_string_embedding.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/b6/4a/b64a6f4223f9ed9a67cd361fed1d927b1d99f707.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/sisap.2008.7"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Approximate similarity search in genomic sequence databases using landmark-guided embedding

Ahmet Sacan, I. Hakki Toroslu
<span title="">2008</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vuw5ktdyknehrehttg5qm4rfqm" style="color: black;">2008 IEEE 24th International Conference on Data Engineering Workshop</a> </i> &nbsp;
The approximate representation is shown to provide several orders of magnitude speed-up in similarity search compared to the exact representation, while maintaining comparable search accuracy.  ...  Similarity search in sequence databases is of paramount importance in bioinformatics research.  ...  We would also like thank the anonymous reviewers for their critical analysis of and corrections to the manuscript.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icdew.2008.4498343">doi:10.1109/icdew.2008.4498343</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icde/SacanT08.html">dblp:conf/icde/SacanT08</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/b2jnwabvtbgg3kr3uxckyfb25e">fatcat:b2jnwabvtbgg3kr3uxckyfb25e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20081031173716/http://www.ceng.metu.edu.tr/~ahmet/Wiki/_media/papers/2008_string_embedding.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/b6/4a/b64a6f4223f9ed9a67cd361fed1d927b1d99f707.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icdew.2008.4498343"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 295,198 results