Filters








469,831 Hits in 5.9 sec

Explanation-based learning: a survey of programs and perspectives

Thomas Ellman
<span title="1989-06-01">1989</span> <i title="Association for Computing Machinery (ACM)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/eiea26iqqjcatatlgxdpzt637y" style="color: black;">ACM Computing Surveys</a> </i> &nbsp;
Explanation-based learning (EBL) is a technique by which an intelligent system can learn by observing examples.  ...  This paper provides a general introduction to the field of explanation-based learning. Considerable emphasis is placed on showing how EBL combines the four learning tasks mentioned above.  ...  This research is surveyed by Angluin and Smith [1983] , Cohen and Feigenbaum [1982], Michalski [1983] , Michalski et al. Fred  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/66443.66445">doi:10.1145/66443.66445</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o25qzli5sza3nczyifhhcl2roi">fatcat:o25qzli5sza3nczyifhhcl2roi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160411033411/http://www.cp.eng.chula.ac.th/~vishnu/gameResearch/AI/p163-ellman.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/4c/3a/4c3a2306d23c5a2823f282c93a10c7625021d369.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/66443.66445"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Explanation-Based Human Debugging of NLP Models: A Survey [article]

Piyawat Lertvittayakumjorn, Francesca Toni
<span title="2021-12-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this survey, we review papers that exploit explanations to enable humans to give feedback and debug NLP models. We call this problem explanation-based human debugging (EBHD).  ...  Debugging a machine learning model is hard since the bug usually involves the training data and the learning process.  ...  the feedback without telling them that the explanations are of the production system (e.g., by asking them to answer a separate survey).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.15135v3">arXiv:2104.15135v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u6equfv2yrbhxeiexyrpzadip4">fatcat:u6equfv2yrbhxeiexyrpzadip4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211215001702/https://arxiv.org/pdf/2104.15135v3.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/d8/4e/d84ed05ab860b75f9e6b28e717abf4bc12da03d7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.15135v3" 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>

Explanation-Based Learning for Planning [chapter]

John Langford, Xinhua Zhang, Gavin Brown, Indrajit Bhattacharya, Lise Getoor, Thomas Zeugmann, Thomas Zeugmann, Ljupčo Todorovski, Kai Ming Ting, David Corne, Julia Handl, Joshua Knowles (+23 others)
<span title="">2011</span> <i title="Springer US"> Encyclopedia of Machine Learning </i> &nbsp;
Synonyms: Explanation-based generalization for planning; Speedup learning for planning.  ...  Definition Explanation Based Learning (EBL) involves using prior knowledge to explain ("prove") why the training example has the label it is given, and using this explanation to guide the learning.  ...  See Also: Speedup Learning, explanation-based learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-0-387-30164-8_297">doi:10.1007/978-0-387-30164-8_297</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mrphhe5tdrbkxct6fv5yr3ex7i">fatcat:mrphhe5tdrbkxct6fv5yr3ex7i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20090116000922/http://rakaposhi.eas.asu.edu/ebl-plan.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/5a/b5/5ab586c472dac612f8ef4c6bc282284d5ab9bf9f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-0-387-30164-8_297"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Preface and Acknowledgements [chapter]

<span title="">1990</span> <i title="Elsevier"> Extending Explanation-Based Learning by Generalizing the Structure of Explanations </i> &nbsp;
Det er vanskelig å si, men jeg vil tippe mellom 100.000-150.000 unike brukere i måneden.  ...  When we consider the political activity of forum users (see table below, based on replies to survey question 06-2), we observe that a clear majority proclaims to be "Not active".  ...  Each checkpoint has a priority level assigned to it, based on its impact on accessibility 13 : [Priority 1] A Web content developer must satisfy this checkpoint.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/b978-0-273-08817-2.50003-0">doi:10.1016/b978-0-273-08817-2.50003-0</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3vbd4xdd7rfsxgwpeqlmbhe7vq">fatcat:3vbd4xdd7rfsxgwpeqlmbhe7vq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20130908221151/http://heim.ifi.uio.no/~simonb/Studier/hfag/FERDIG/CD/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/00/8d/008d479d3386747d32c8e93be528858e61166a6f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/b978-0-273-08817-2.50003-0"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Empirically Evaluating EBL [chapter]

Jude W. Shavlik, Paul O'Rorke
<span title="">1993</span> <i title="Springer US"> Investigating Explanation-Based Learning </i> &nbsp;
Methods: This cross-sectional study was conducted through a survey and included all 50 Jundishapur University of Medical Sciences' librarians.  ...  A researcher-made questionnaire was utilized for the survey and the face validity and reliability was confirmed by Cronbach's alpha coefficient 0.75.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-1-4615-3602-4_7">doi:10.1007/978-1-4615-3602-4_7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w54gsaqnyvg4hnfj2deirvpwue">fatcat:w54gsaqnyvg4hnfj2deirvpwue</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200318091411/https://bmjopen.bmj.com/content/bmjopen/7/Suppl_1/bmjopen-2016-015415.54.full.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/5c/b5/5cb5fc0018e56fc24bfc183c813e341c87932b6e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-1-4615-3602-4_7"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Score-Based Explanations in Data Management and Machine Learning [article]

Leopoldo Bertossi
<span title="2020-08-19">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We describe some approaches to explanations for observed outcomes in data management and machine learning.  ...  More specifically, we consider explanations for query answers in databases, and for results from classification models. The described approaches are mostly of a causal and counterfactual nature.  ...  Bertossi is a member of the Academic Network of RelationalAI Inc., where his interest in explanations in ML started.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.12799v2">arXiv:2007.12799v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yue3oo7hl5hf5gjvuj7ps6sufy">fatcat:yue3oo7hl5hf5gjvuj7ps6sufy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201013190247/https://arxiv.org/pdf/2007.12799v2.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/5e/ec5ec0e41a971f481ed8bd8a668bb72b5f609cb3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.12799v2" 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>

Learning to Deceive with Attention-Based Explanations [article]

Danish Pruthi, Mansi Gupta, Bhuwan Dhingra, Graham Neubig, Zachary C. Lipton
<span title="2020-04-06">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Through a human study, we show that our manipulated attention-based explanations deceive people into thinking that predictions from a model biased against gender minorities do not rely on the gender.  ...  Consequently, our results cast doubt on attention's reliability as a tool for auditing algorithms in the context of fairness and accountability.  ...  ZL thanks Amazon AI, NVIDIA, Salesforce, Facebook AI, AbridgeAI, UPMC, the Center for Machine Learning in Health, the PwC Center, the AI Ethics and Governance Fund, and DARPA's Learning with Less Labels  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.07913v2">arXiv:1909.07913v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lhtvktu3wvbath7ubzqyvoexuq">fatcat:lhtvktu3wvbath7ubzqyvoexuq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200415232655/https://arxiv.org/pdf/1909.07913v2.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/1909.07913v2" 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>

Interactive Explanations: Diagnosis and Repair of Reinforcement Learning Based Agent Behaviors [article]

Christian Arzate Cruz, Takeo Igarashi
<span title="2021-05-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Reinforcement learning techniques successfully generate convincing agent behaviors, but it is still difficult to tailor the behavior to align with a user's specific preferences.  ...  In this paper, we present a novel interaction method that uses interactive explanations using templates of natural language as a communication method.  ...  In particular, we use the work by [28] as a basis to implement our interactive explanation system. Therefore, our Super Mario Bros. bot uses a model-based reinforcement learning algorithm.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.12938v1">arXiv:2105.12938v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kone5o4pdjewhd7hxyswmidl74">fatcat:kone5o4pdjewhd7hxyswmidl74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210530181738/https://arxiv.org/pdf/2105.12938v1.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/56/67/566754e9440a5bb592f4d490b4ab93a331cf0769.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.12938v1" 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>

[Re] Reproducing Learning to Deceive With Attention-Based Explanations

Rahel Habacker, Andrew Harrison, Mathias Parisot, Ard Snijders
<span title="2021-05-28">2021</span> <i title="Zenodo"> Zenodo </i> &nbsp;
Based on the intuition that attention in neural networks is what the model focuses on, attention is now being used as an explanation for a models' prediction (see Galassi, Lippi, and Torroni 1 for a survey  ...  -Habacker et al. 2021 [Re] Reproducing Learning to Deceive With Attention-Based Explanations els can learn to deceive.  ...  This research thus provides a new vein of the investigation into the attention-based explanation debate.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.4834146">doi:10.5281/zenodo.4834146</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dsib5ae6dbfx3kffnag6bxvssi">fatcat:dsib5ae6dbfx3kffnag6bxvssi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210601214758/https://zenodo.org/record/4834146/files/article.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/ed/80/ed80a8888bcd3a8adf2ca784a5699969eaa597da.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.4834146"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Score-Based Explanations in Data Management and Machine Learning: An Answer-Set Programming Approach to Counterfactual Analysis [article]

Leopoldo Bertossi
<span title="2021-09-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We describe some recent approaches to score-based explanations for query answers in databases and outcomes from classification models in machine learning.  ...  Special emphasis is placed on declarative approaches based on answer-set programming to the use of counterfactual reasoning for score specification and computation.  ...  Bertossi has been a member of the Academic Network of RelationalAI Inc., where his interest in explanations in ML started.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.10562v2">arXiv:2106.10562v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pb63d7kyo5e6jn6yu5mipyproy">fatcat:pb63d7kyo5e6jn6yu5mipyproy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210623233524/https://arxiv.org/pdf/2106.10562v1.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/e2/8e/e28e011672398b1d7e6188b6cf331f7652fc5c9e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.10562v2" 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>

What Would You Ask the Machine Learning Model? Identification of User Needs for Model Explanations Based on Human-Model Conversations [article]

Michał Kuźba, Przemysław Biecek
<span title="2020-07-31">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this experiment, we developed a chatbot called dr_ant to talk about machine learning model trained to predict survival odds on Titanic.  ...  The analysis of needs, if done, takes the form of an A/B test rather than a study of open questions. To answer the question "What would a human operator like to ask the ML model?"  ...  To address these problems we create an open-ended dialog based explanation system. We develop a chatbot allowing the explainee to interact with a predictive model and its explanations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.05674v3">arXiv:2002.05674v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3ewsvzv3fzg6dgvmihydkrxrhq">fatcat:3ewsvzv3fzg6dgvmihydkrxrhq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200925124906/https://arxiv.org/pdf/2002.05674v3.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/89/98/899837ac827beb9f32e7628b98f6399873739754.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.05674v3" 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>

Explainable Reinforcement Learning: A Survey [article]

Erika Puiutta, Eric MSP Veith
<span title="2020-05-13">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Since, to the best of our knowledge, there exists no single work offering an overview of Explainable Reinforcement Learning (XRL) methods, this survey attempts to address this gap.  ...  Thus, an interdisciplinary effort is needed to adapt the generated explanations to a (non-expert) human user in order to effectively progress in the field of XRL and XAI in general.  ...  Method C: Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees In Liu et al. [38] , a mimic learning framework based on stochastic gradient descent is introduced.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.06247v1">arXiv:2005.06247v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5qqohnjnongqbhovks3w5mx26e">fatcat:5qqohnjnongqbhovks3w5mx26e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200515053951/https://arxiv.org/pdf/2005.06247v1.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/2005.06247v1" 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>

Discovery learning, representation, and explanation within a computer-based simulation: finding the right mix

Lloyd P. Rieber, Shyh-Chii Tzeng, Kelly Tribble
<span title="">2004</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/xtksveiworabxaudztwrgtz5mi" style="color: black;">Learning and Instruction</a> </i> &nbsp;
The purpose of this research was to explore how adult users interact and learn during an interactive computer-based simulation supplemented with brief multimedia explanations of the content.  ...  A total of 52 college students interacted with a computer-based simulation of Newton's laws of motion in which they had control over the motion of a simple screen object-an animated ball.  ...  After each simulation try, the computer surveyed participants on their level of frustration.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.learninstruc.2004.06.008">doi:10.1016/j.learninstruc.2004.06.008</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qq73uomx5ba5xnrnxmz2uamasm">fatcat:qq73uomx5ba5xnrnxmz2uamasm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808074047/http://tecfa.unige.ch/tecfa/teaching/staf11/textes/rieber04.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/e2/70/e27076133a9671be234b66d398f5e25b2d6fe111.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.learninstruc.2004.06.008"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

A Survey of Explainable Reinforcement Learning [article]

Stephanie Milani and Nicholay Topin and Manuela Veloso and Fei Fang
<span title="2022-02-17">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this survey, we propose a novel taxonomy for organizing the XRL literature that prioritizes the RL setting. We overview techniques according to this taxonomy.  ...  Explainable reinforcement learning (XRL) is an emerging subfield of explainable machine learning that has attracted considerable attention in recent years.  ...  We present a comprehensive survey of XRL literature, organized based on our novel proposed taxonomy.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.08434v1">arXiv:2202.08434v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uewmjhgnkbcxdctj673ahalc3y">fatcat:uewmjhgnkbcxdctj673ahalc3y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220219013559/https://arxiv.org/pdf/2202.08434v1.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/b1/5c/b15c250f1e74a4627f3a79b589de698293bed32b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.08434v1" 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>

Backdoor Learning: A Survey [article]

Yiming Li, Yong Jiang, Zhifeng Li, Shu-Tao Xia
<span title="2022-02-16">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We summarize and categorize existing backdoor attacks and defenses based on their characteristics, and provide a unified framework for analyzing poisoning-based backdoor attacks.  ...  Although backdoor learning is an emerging and rapidly growing research area, its systematic review, however, remains blank. In this paper, we present the first comprehensive survey of this realm.  ...  ACKNOWLEDGEMENTS This work was partly done when Yiming Li was a research intern at Tencent AI Lab, supported by the Tencent Rhino-Bird Elite Training Program (2020).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.08745v5">arXiv:2007.08745v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5vffxzvh7bdb5nz7qlrytssowi">fatcat:5vffxzvh7bdb5nz7qlrytssowi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220218130258/https://arxiv.org/pdf/2007.08745v5.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/fa/a4/faa48bc9d554505bb542c03a99bbf52ca2b599e3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.08745v5" 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 469,831 results