Filters








27,772 Hits in 6.4 sec

Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey [article]

Sanmit Narvekar and Bei Peng and Matteo Leonetti and Jivko Sinapov and Matthew E. Taylor and Peter Stone
<span title="2020-09-17">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this article, we present a framework for curriculum learning (CL) in reinforcement learning, and use it to survey and classify existing CL methods in terms of their assumptions, capabilities, and goals  ...  Finally, we use our framework to find open problems and suggest directions for future RL curriculum learning research.  ...  Acknowledgments We would like to sincerely thank Brad Knox, Garrett Warnell, and the anonymous reviewers for helpful comments and suggestions that improved the presentation of many ideas in this article  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.04960v2">arXiv:2003.04960v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/iacmqeb7jjeezpo27jsnzuqb7u">fatcat:iacmqeb7jjeezpo27jsnzuqb7u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928013643/https://arxiv.org/pdf/2003.04960v2.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/2003.04960v2" 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>

Accelerating Reinforcement Learning for Reaching using Continuous Curriculum Learning [article]

Sha Luo, Hamidreza Kasaei, Lambert Schomaker
<span title="2020-02-07">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Experimental results support the hypothesis that a static training schedule is suboptimal, and using an appropriate decay function for curriculum learning provides superior results in a faster way.  ...  To this end, we explore various continuous curriculum strategies for controlling a training process.  ...  Marco Wiering for his thoughtful suggestions. We also thank Weijia Yao for the fruitful discussion about the experimental design and the useful comments for the paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.02697v1">arXiv:2002.02697v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2hlk46k5mzdunnylbsxe23kiii">fatcat:2hlk46k5mzdunnylbsxe23kiii</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321153611/https://arxiv.org/pdf/2002.02697v1.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/2002.02697v1" 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>

Evolutionarily-Curated Curriculum Learning for Deep Reinforcement Learning Agents [article]

Michael Cerny Green, Benjamin Sergent, Pushyami Shandilya, Vibhor Kumar
<span title="2019-01-16">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper we propose a new training loop for deep reinforcement learning agents with an evolutionary generator.  ...  Evolutionary procedural content generation has been used in the creation of maps and levels for games before.  ...  In Section 3 we discuss the theory of evolutionarily-based curriculum learning and how it could be applied to a reinforcement learning agent.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.05431v1">arXiv:1901.05431v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/35nqdu7ljra2zinbjmv2dp6xj4">fatcat:35nqdu7ljra2zinbjmv2dp6xj4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824221813/https://arxiv.org/pdf/1901.05431v1.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/84/af/84af483d6dc9706288b9c107d051f89ddb4079e1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.05431v1" 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>

Goal-constrained Sparse Reinforcement Learning for End-to-End Driving [article]

Pranav Agarwal, Pierre de Beaucorps, Raoul de Charette
<span title="2021-07-31">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we explore full-control driving with only goal-constrained sparse reward and propose a curriculum learning approach for end-to-end driving using only navigation view maps that benefit from  ...  Deep reinforcement Learning for end-to-end driving is limited by the need of complex reward engineering.  ...  Overview of our reinforcement learning framework for end to end driving with sparse reward.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.09189v2">arXiv:2103.09189v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tbodnetl6beltbpmsxtqtq6viq">fatcat:tbodnetl6beltbpmsxtqtq6viq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210804133540/https://arxiv.org/pdf/2103.09189v2.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/f5/35/f5356afe2b7dee2114957c451deceb03a6a15672.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.09189v2" 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>

Policy Search in Continuous Action Domains: an Overview [article]

Olivier Sigaud, Freek Stulp
<span title="2019-06-13">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we present a broad survey of policy search methods, providing a unified perspective on very different approaches, including also Bayesian Optimization and directed exploration methods.  ...  Continuous action policy search is currently the focus of intensive research, driven both by the recent success of deep reinforcement learning algorithms and the emergence of competitors based on evolutionary  ...  We thank David Filliat, Nicolas Perrin and Pierre-Yves Oudeyer for their feedback on this article.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.04706v5">arXiv:1803.04706v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/llh4j5js5reopegwduelivxxm4">fatcat:llh4j5js5reopegwduelivxxm4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191221212551/https://arxiv.org/pdf/1803.04706v5.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/20/67/2067e5dbeb83da18abfb756b78b48495b5185d0a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.04706v5" 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>

Characteristics of global naturopathic education, regulation, and practice frameworks: results from an international survey

J M Dunn, A E Steel, J Adams, I Lloyd, N De Groot, T Hausser, J Wardle
<span title="2021-02-18">2021</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7ggsqn5oarf27f2ndlqmi66apy" style="color: black;">BMC Complementary Medicine and Therapies</a> </i> &nbsp;
Despite increasing public use, a significant workforce, and World Health Organization calls for national policy development to support integration of services, existent frameworks as potential barriers  ...  Education and regulation of the naturopathic profession has significant heterogeneity, even in the face of global calls for consistent regulation that recognizes naturopathy as a medical system.  ...  Tabatha Parker (USA), and Dr. Surya Karki (Nepal) for local support provided.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s12906-021-03217-1">doi:10.1186/s12906-021-03217-1</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33602181">pmid:33602181</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u6kqwqpj3bec3ci6z2ng5ovxyy">fatcat:u6kqwqpj3bec3ci6z2ng5ovxyy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210715153031/https://opus.lib.uts.edu.au/bitstream/10453/147798/2/Characteristics%20of%20global%20naturopathic%20education%2c%20regulation%2c%20and%20practice%20frameworks%20results%20from%20an%20international%20survey.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/21/b8/21b8755f6287935d9de0df78e6bfe9a1b510ef8c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s12906-021-03217-1"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>

Policy search in continuous action domains: An overview

Olivier Sigaud, Freek Stulp
<span title="">2019</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/oml24fsyizfuhn3rn5np75ubdi" style="color: black;">Neural Networks</a> </i> &nbsp;
Continuous action policy search is currently the focus of intensive research, driven both by the recent success of deep reinforcement learning algorithms and the emergence of competitors based on evolutionary  ...  In this paper, we present a broad survey of policy search methods, providing a unified perspective on very different approaches, including also Bayesian Optimization and directed exploration methods.  ...  We thank David Filliat, Nicolas Perrin and Pierre-Yves Oudeyer for their feedback on this article.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.neunet.2019.01.011">doi:10.1016/j.neunet.2019.01.011</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/itzh3ogmgfdahomr3gjlduvkbq">fatcat:itzh3ogmgfdahomr3gjlduvkbq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200306152103/https://hal.sorbonne-universite.fr/hal-02182466/file/1803.04706.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/c6/c4c69cf10c201831e0bf53047a6ff8996d664dd0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.neunet.2019.01.011"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Curriculum Learning for Domain Adaptation in Neural Machine Translation [article]

Xuan Zhang, Pamela Shapiro, Gaurav Kumar, Paul McNamee, Marine Carpuat, Kevin Duh
<span title="2019-05-14">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We introduce a curriculum learning approach to adapt generic neural machine translation models to a specific domain.  ...  This approach is simple to implement on top of any neural framework or architecture, and consistently outperforms both unadapted and adapted baselines in experiments with two distinct domains and two language  ...  Acknowledgments This work is supported in part by a AWS Machine Learning Research Award and a grant from the Office of the Director of National Intelligence, Intelligence Advanced Research Projects Activity  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1905.05816v1">arXiv:1905.05816v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/whe5u5rorzhetdoaj34c3juhkq">fatcat:whe5u5rorzhetdoaj34c3juhkq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200903235509/https://arxiv.org/pdf/1905.05816v1.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/87/78/87786023757de8d7af1d17c9841fd28c2c787e29.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1905.05816v1" 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>

Domain-specific Knowledge Graphs: A survey [article]

Bilal Abu-Salih
<span title="2021-03-03">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This survey is the first to offer a comprehensive definition of a domain-specific KG.  ...  However, there is no consensus in regard to a plausible and inclusive definition of a domain-specific KG.  ...  By using standard curriculum and learning assessment data as data sources, and by using neural network models for concepts and relations identification, KnowEdu is created to facilitate learner's cognitive  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.00235v3">arXiv:2011.00235v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oc2loewqdjfgvlapy4kmult5li">fatcat:oc2loewqdjfgvlapy4kmult5li</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108002055/https://arxiv.org/ftp/arxiv/papers/2011/2011.00235.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/fc/64/fc6479a39fefb7814acfcfc8d277659c43ca6e02.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.00235v3" 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>

Curriculum Learning for Domain Adaptation in Neural Machine Translation

Xuan Zhang, Pamela Shapiro, Gaurav Kumar, Paul McNamee, Marine Carpuat, Kevin Duh
<span title="">2019</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/d5ex6ucxtrfz3clshlkh3f6w2q" style="color: black;">Proceedings of the 2019 Conference of the North</a> </i> &nbsp;
We introduce a curriculum learning approach to adapt generic neural machine translation models to a specific domain.  ...  This approach is simple to implement on top of any neural framework or architecture, and consistently outperforms both unadapted and adapted baselines in experiments with two distinct domains and two language  ...  Acknowledgments This work is supported in part by a AWS Machine Learning Research Award and a grant from the Office of the Director of National Intelligence, Intelligence Advanced Research Projects Activity  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/n19-1189">doi:10.18653/v1/n19-1189</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/naacl/ZhangSKMCD19.html">dblp:conf/naacl/ZhangSKMCD19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ocx4x2burrdkfnqwoz3cl3tahe">fatcat:ocx4x2burrdkfnqwoz3cl3tahe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200508030137/https://www.aclweb.org/anthology/N19-1189.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/99/ec9984003962eb70a73bf0882ab49ef38cd6c239.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/n19-1189"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Unsupervised Domain Adaptation in Semantic Segmentation: a Review [article]

Marco Toldo, Andrea Maracani, Umberto Michieli, Pietro Zanuttigh
<span title="2020-05-21">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
analysis of the classifier discrepancies, self-teaching, entropy minimization, curriculum learning and multi-task learning.  ...  The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation.  ...  In [100] the connection between curriculum learning and self-training is highlighted and a method (called self-motivated pyramid curriculum domain adaptation, PyCDA) that uses and merges both techniques  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.10876v1">arXiv:2005.10876v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7t5v6qibxnfcxhwtohqqunhd2u">fatcat:7t5v6qibxnfcxhwtohqqunhd2u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200527095059/https://arxiv.org/pdf/2005.10876v1.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/b4/25/b4255c0bc1ae0eef07b2d38c3271646f9b3bff60.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.10876v1" 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>

Neural Dialogue Generation Methods in Open Domain: A Survey

Bin Sun, Kan Li
<span title="">2021</span> <i title="Atlantis Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/bw7tmfwibbc6rhclbhaiapjdqu" style="color: black;">Natural Language Processing Research</a> </i> &nbsp;
Since most daily conversations cannot be described by rules or frames, it is difficult for a dialogue system based on rules and frameworks to meet the needs of an open-domain dialogue task.  ...  At first stage, many dialogue systems are based on rules and frames, that is, the related keywords are set in advance, and a response framework is designed for these keywords.  ...  ACKNOWLEDGMENTS We are grateful to the anonymous reviewers for their valuable and constructional advices on the previous versions of this article; all remaining errors are our own.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2991/nlpr.d.210223.001">doi:10.2991/nlpr.d.210223.001</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mqcjkf7vczfkdjhdtbznupmz2e">fatcat:mqcjkf7vczfkdjhdtbznupmz2e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210320163126/https://www.atlantis-press.com/article/125954217.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/14/83/1483a95a0b98c57feb8f1a8b49348a90d5b79f8e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2991/nlpr.d.210223.001"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Examining Domains of Technological Pedagogical Content Knowledge Using Factor Analysis

Valerie Harlow Shinas, Sule Yilmaz-Ozden, Chrystalla Mouza, Rachel Karchmer-Klein, Joseph J. Glutting
<span title="">2013</span> <i title="Informa UK Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vd24pqhprvhinmuuj526a55x5u" style="color: black;">Journal of Research on Technology in Education</a> </i> &nbsp;
Although the influence of the TPACK framework on teacher education programs continues to grow, research indicates the need for clearer distinctions between the domains.  ...  The survey, grounded in the framework of Technological Pedagogical Content Knowledge (TPACK), is designed to measure seven domains associated with technological, pedagogical, and content knowledge.  ...  For example, participants are explicitly introduced to the TPACK framework as a means for designing curriculum-based, technology-integrated lessons.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1080/15391523.2013.10782609">doi:10.1080/15391523.2013.10782609</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rjgu5xob55abvmkkz6en6ds3ai">fatcat:rjgu5xob55abvmkkz6en6ds3ai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150409220703/http://files.eric.ed.gov/fulltext/EJ1010668.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/70/09/7009f370f0e56867d85f03ad3b32ed3c9eb0e919.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1080/15391523.2013.10782609"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> tandfonline.com </button> </a>

Unsupervised Domain Adaptation in Semantic Segmentation: A Review

Marco Toldo, Andrea Maracani, Umberto Michieli, Pietro Zanuttigh
<span title="2020-06-21">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ccathu4omjd55by7ulzsocssly" style="color: black;">Technologies</a> </i> &nbsp;
analysis of the classifier discrepancies, self-teaching, entropy minimization, curriculum learning and multi-task learning.  ...  The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation.  ...  In [101] , the connection between curriculum learning and self-training is highlighted and a method (called self-motivated pyramid curriculum domain adaptation, PyCDA) that uses and merges both techniques  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/technologies8020035">doi:10.3390/technologies8020035</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qzgjjiw5p5bldk76mh3s3pwlfq">fatcat:qzgjjiw5p5bldk76mh3s3pwlfq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200623031424/https://res.mdpi.com/d_attachment/technologies/technologies-08-00035/article_deploy/technologies-08-00035.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/a6/45/a645ae680fd6ee9213d1c5176fb3a31822b614a5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/technologies8020035"> <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>

Unsupervised Domain Adaptation of Object Detectors: A Survey [article]

Poojan Oza, Vishwanath A. Sindagi, Vibashan VS, Vishal M. Patel
<span title="2021-07-04">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Here, we describe in detail the domain adaptation problem for detection and present an extensive survey of the various methods.  ...  Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and detection.  ...  [121] Adversarial feature learning Image-to-image translation Domain randomization Roychowdhury et al. [61] Khodabandeh et al. [62] Kim et al. [97] D'Innocente et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.13502v2">arXiv:2105.13502v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ozzbbvoflfdvjdewjnjmfajlpa">fatcat:ozzbbvoflfdvjdewjnjmfajlpa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210709083545/https://arxiv.org/pdf/2105.13502v2.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/96/bb/96bb5e0ee886b499e5d6d64b4636bc7be343ccc0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.13502v2" 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 27,772 results