Internet Archive Scholar
Filters
























7 Hits in 6.7 sec

Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling [article]

K. Darshana Abeyrathna, Bimal Bhattarai, Morten Goodwin, Saeed Gorji, Ole-Christoffer Granmo, Lei Jiao, Rupsa Saha, Rohan K. Yadav
<span title="2021-06-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

Web Archive Capture PDF (1.6 MB)
https://web.archive.org/web/20200929034456/https://arxiv.org/pdf/2009.04861v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2009.04861v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

<span title="2020-09-13">2020</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.04861v2">arXiv:2009.04861v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xvxvje26xzef7arp4e5p74s7em">fatcat:xvxvje26xzef7arp4e5p74s7em</a> </span>

Other Versions

<span title="2020-09-10">2020</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.04861v1">arXiv:2009.04861v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7fxv4y2e7vcw3jrnmvmzfd7z6m">fatcat:7fxv4y2e7vcw3jrnmvmzfd7z6m</a> </span>
<span title="2021-02-03">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.04861v3">arXiv:2009.04861v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/er4hucoiybehfnhpwaj5wraodu">fatcat:er4hucoiybehfnhpwaj5wraodu</a> </span>
Our parallel and asynchronous architecture thus allows processing of massive datasets and operating with more clauses for higher accuracy.  ...  Finally, learning time is almost constant for reasonable clause amounts (employing from 20 to 7,000 clauses on a Tesla V100 GPU).  ...  Then, in Section 3, we propose a novel parallel and asynchronous architecture where every clause runs in its own thread for massive parallelism.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.04861v4">arXiv:2009.04861v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5fe3u72tnjdipabclskosplg3m">fatcat:5fe3u72tnjdipabclskosplg3m</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929034456/https://arxiv.org/pdf/2009.04861v2.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/2009.04861v4" 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>
Citation

K. Darshana Abeyrathna, Bimal Bhattarai, Morten Goodwin, Saeed Gorji, Ole-Christoffer Granmo, Lei Jiao, Rupsa Saha, Rohan K. Yadav. "Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling." arXiv (2021)

Reinforcement Learning: A Survey

L. P. Kaelbling, M. L. Littman, A. W. Moore
<span title="1996-05-01">1996</span> <i title="AI Access Foundation"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/4ax4efcwajcgvidb6hcg6mwx4a" style="color: black;">The Journal of Artificial Intelligence Research</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (523.4 kB)
https://web.archive.org/web/20190426102937/https://jair.org/index.php/jair/article/download/10166/24110

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://jair.org/index.php/jair/article/download/10166/24110">the original URL</a>. The file type is <code>application/pdf</code>.

It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized.  ...  reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.  ...  Leslie Pack Kaelbling was supported in part by NSF grants IRI-9453383 and IRI-9312395. Michael Littman was supported in part by Bellcore.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1613/jair.301">doi:10.1613/jair.301</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nbo23vmu6rfz3ctpjbk7sdcnt4">fatcat:nbo23vmu6rfz3ctpjbk7sdcnt4</a> </span>
<span class="ui label basic orange small" title="Directory of Open Access Journals">DOAJ</span> <span class="ui label basic orange small" title="Szcezepanski OA Journal List">Szczepanski</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190426102937/https://jair.org/index.php/jair/article/download/10166/24110" 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/12/d1/12d1d070a53d4084d88a77b8b143bad51c40c38f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1613/jair.301"> <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>
Citation

L. P. Kaelbling, M. L. Littman, A. W. Moore. "Reinforcement Learning: A Survey." The Journal of Artificial Intelligence Research (1996) 237-285

Reinforcement Learning: A Survey [article]

L. P. Kaelbling, M. L. Littman, A. W. Moore
<span title="1996-05-01">1996</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
File Archive PDF (506.5 kB)
https://archive.org/download/arxiv-cs9605103/cs9605103.pdf

The Internet Archive has a preservation copy of this work in our general collections. The file type is <code>application/pdf</code>.

It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized.  ...  reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.  ...  Leslie Pack Kaelbling was supported in part by NSF grants IRI-9453383 and IRI-9312395. Michael Littman was supported in part by Bellcore.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/cs/9605103v1">arXiv:cs/9605103v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ze737h6wnfdhjf52hiz4gpogxq">fatcat:ze737h6wnfdhjf52hiz4gpogxq</a> </span>
<a target="_blank" rel="noopener" href="https://archive.org/download/arxiv-cs9605103/cs9605103.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> File Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/29/54/2954bbb4666ef55d20c9968a952ac8bf980aae38.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/cs/9605103v1" 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>
Citation

L. P. Kaelbling, M. L. Littman, A. W. Moore. "Reinforcement Learning: A Survey." arXiv (1996)

Quantum Mind 2003, Consciousness, Quantum Physics and the Brain. March 15-19, 2003, The University of Arizona, Tucson, Arizona

Editorial NQ
<span title="2007-09-04">2007</span> <i title="NeuroQuantology Journal"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfjjshkdo5eynaqtxbx53v4cy4" style="color: black;">NeuroQuantology</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (739.3 kB)
https://web.archive.org/web/20170921232957/https://www.neuroquantology.com/index.php/journal/article/download/23/23

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="https://www.neuroquantology.com/index.php/journal/article/download/23/23">the original URL</a>. The file type is <code>application/pdf</code>.

At the same time quantum processes (superposition of states, nonlocality, entanglement...) also remain mysterious, yet are being harnessed in revolutionary information technologies (quantum computation  ...  A relation between consciousness and quantum effects has been pondered for nearly a century, and in the past decades quantum processes in the brain have been invoked as explanations for consciousness and  ...  This is between 10to18 up to 10to19 x Planck's constant, which is in good agreement with the time-scale differences for neural state decoherence and spiking time calculated by Tegmark (10to19 s).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14704/nq.2003.1.3.23">doi:10.14704/nq.2003.1.3.23</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/e76cv2ivqjdbxolv2hbls67gqu">fatcat:e76cv2ivqjdbxolv2hbls67gqu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170921232957/https://www.neuroquantology.com/index.php/journal/article/download/23/23" 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/ca/51/ca5118e730bc0fedde75826a7f0c7cfbbe5ee6c3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14704/nq.2003.1.3.23"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Editorial NQ. "Quantum Mind 2003, Consciousness, Quantum Physics and the Brain. March 15-19, 2003, The University of Arizona, Tucson, Arizona." NeuroQuantology 1.3 (2007)

Effective Policy Search Method for Robot Reinforcement Learning with Noisy Reward
노이즈 환경에서 효과적인 로봇 강화 학습의 정책 탐색 방법

Young-Ha Yang, Cheol-Soo Lee
<span title="2022-03-01">2022</span> <i title="The Korea Robotics Society"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/v2e5pfzr7ncnznd24dd2oqmw7i" style="color: black;">The Journal of Korea Robotics Society</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.2 MB)
https://web.archive.org/web/20220331225625/https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

We also wish to thank the many people who have read drafts of this book and provided valuable comments, including  ...  2 We restrict attention to discrete time to keep things as simple as possible, even though many of the ideas can be extended to the continuous-time case (e.g., see Bertsekas and Tsitsiklis, 1996; Werbos  ...  , 1992; Doya, 1996) . 3 We use R t+1 instead of R t to denote the reward due to A t because it emphasizes that the next reward and next state, R t+1 and S t+1 , are jointly determined.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.7746/jkros.2022.17.1.001">doi:10.7746/jkros.2022.17.1.001</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r44kgqjsyrcq7pnyk4ylrwigwq">fatcat:r44kgqjsyrcq7pnyk4ylrwigwq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220331225625/https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.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/37/72/3772e468e3ed4d00571818d693b522978e368172.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.7746/jkros.2022.17.1.001"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Young-Ha Yang, Cheol-Soo Lee. "Effective Policy Search Method for Robot Reinforcement Learning with Noisy Reward." The Journal of Korea Robotics Society 17.1 (2022) 1-7

Return from the ant

Sven Brückner, Humboldt-Universität Zu Berlin, Humboldt-Universität Zu Berlin
<span title="2017-06-18">2017</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.1 MB)
https://web.archive.org/web/20220123110101/https://edoc.hu-berlin.de/bitstream/handle/18452/15267/Brueckner.pdf;jsessionid=0172861EBF9E35D7E79DF3223996FDD6?sequence=1

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://edoc.hu-berlin.de/bitstream/handle/18452/15267/Brueckner.pdf;jsessionid=0172861EBF9E35D7E79DF3223996FDD6?sequence=1">the original URL</a>. The file type is <code>application/pdf</code>.

Sign-based stigmergy through synthetic pheromones is supported by an extension to runtime environments for software agents called the pheromone infrastructure.  ...  Each principle is systematically stated and motivated, and its consequences for the manufacturing control domain are discussed.  ...  There is almost never an agent able to perform a task alone. In a consequently decentralized and asynchronous system, tasks arise in parallel.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18452/14615">doi:10.18452/14615</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r4vwampyrvatlj4j722f5zuela">fatcat:r4vwampyrvatlj4j722f5zuela</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220123110101/https://edoc.hu-berlin.de/bitstream/handle/18452/15267/Brueckner.pdf;jsessionid=0172861EBF9E35D7E79DF3223996FDD6?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/6a/47/6a471956bd6c004c5891c2b904d5ce0b5c50ecca.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18452/14615"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Sven Brückner, Humboldt-Universität Zu Berlin, Humboldt-Universität Zu Berlin. "Return from the ant." (2017)

Towards Fault Reactiveness in Wireless Sensor Networks with Mobile Carrier Robots

Rafael Jesus Falcon Martinez, Université D'Ottawa / University Of Ottawa, Université D'Ottawa / University Of Ottawa
<span title="2012-04-04">2012</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.1 MB)
https://web.archive.org/web/20200221081359/https://ruor.uottawa.ca/bitstream/10393/22685/3/Falcon_Martinez_Rafael_Jesus_2012_thesis.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://ruor.uottawa.ca/bitstream/10393/22685/3/Falcon_Martinez_Rafael_Jesus_2012_thesis.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

It is energy-efficient, fault-reactive and aware of the bounded robot cargo capacity.  ...  They are able to find good-quality solutions in a short time. Two frameworks for the identification of the damaged nodes are considered.  ...  It is known that sensing devices are massively manufactured nowadays because of their simple yet fairly feeble architecture.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.20381/ruor-5569">doi:10.20381/ruor-5569</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dtmqgbyx7zhgvovjnbaznncryq">fatcat:dtmqgbyx7zhgvovjnbaznncryq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200221081359/https://ruor.uottawa.ca/bitstream/10393/22685/3/Falcon_Martinez_Rafael_Jesus_2012_thesis.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/a2/eca281d957f850f801bc4a537cdfce0187ca6ec8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.20381/ruor-5569"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
Citation

Rafael Jesus Falcon Martinez, Université D'Ottawa / University Of Ottawa, Université D'Ottawa / University Of Ottawa. "Towards Fault Reactiveness in Wireless Sensor Networks with Mobile Carrier Robots." (2012)