Filters








217 Hits in 7.2 sec

Meta-Neighborhoods [article]

Siyuan Shan and Yang Li and Junier Oliva
<span title="2020-10-13">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we step forward in this direction and propose a semi-parametric method, Meta-Neighborhoods, where predictions are made adaptively to the neighborhood of the input.  ...  A meta-learning based training mechanism is then exploited to jointly learn the induced neighborhoods and the model. Extensive studies demonstrate the superiority of our method.  ...  The main body of Meta-Neighborhoods is a parametric neural network, but we adapt its parameters to a local neighborhood in a non-parametric scheme.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.09140v3">arXiv:1909.09140v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zgoodo4azja7jkyonn4r76tx3i">fatcat:zgoodo4azja7jkyonn4r76tx3i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201023105050/https://arxiv.org/pdf/1909.09140v3.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/97/94/9794e0f91ff8bd6e006b0c18b3667d1cb8fcb773.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.09140v3" 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>

Measure Theoretic Approach to Nonuniform Learnability [article]

Ankit Bandyopadhyay
<span title="2020-11-01">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Where nonuniform learnability is a strict relaxation of the Probably Approximately Correct framework.  ...  Introduction of a new algorithm, Generalize Measure Learnability framework, to implement this approach with the study of its sample and computational complexity bounds.  ...  We are now in a very position to administer one formalization of this informal claim: it's simply the very fact that GML with their already established preference for 'simple' models with small parametric  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.00392v1">arXiv:2011.00392v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/spqxwqrcmfeubotldynn4af6li">fatcat:spqxwqrcmfeubotldynn4af6li</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201104035940/https://arxiv.org/pdf/2011.00392v1.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/98/71/9871dea4e87b180cf7d55baf26be99b48567bb99.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.00392v1" 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>

Adversarial Examples and Metrics [article]

Nico Döttling, Kathrin Grosse, Michael Backes, Ian Molloy
<span title="2020-07-15">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Concretely, we construct a classification problem, which admits robust classification by a small classifier if the target metric is known at the time the model is trained, but for which robust classification  ...  is impossible for small classifiers if the target metric is chosen after the fact.  ...  Acknowledgments This work was supported by the German Federal Ministry of Education and Research (BMBF) through funding for the Center for IT-Security, Privacy and Accountability (CISPA) (FKZ: 16KIS0753  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.06993v2">arXiv:2007.06993v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rz634goiejh6tcpnjwnz4xzasq">fatcat:rz634goiejh6tcpnjwnz4xzasq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200717082407/https://arxiv.org/pdf/2007.06993v2.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/2007.06993v2" 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 with Restricted Focus of Attention

Shai Ben-David, Eli Dichterman
<span title="">1998</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/p6ovb2qpkfenhmb7mcksobrcxq" style="color: black;">Journal of computer and system sciences (Print)</a> </i> &nbsp;
Although it is a natural refinement of the PAC learning model, some of the fundamental PAC-learning results and techniques fail in the RFA paradigm; learnability in the RFA model is no longer characterized  ...  We also prove the k-RFA learnability of richer classes of Boolean functions (such as k-decision lists) with respect to a given distribution and the efficient (n&1)-RFA learnability (for fixed n), under  ...  ACKNOWLEDGMENTS We thank Alon Itai and Eli Shamir for providing us with helpful comments concerning the work presented in this paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1006/jcss.1998.1569">doi:10.1006/jcss.1998.1569</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/j5ps4sux45cfdk27rcfhbclqhu">fatcat:j5ps4sux45cfdk27rcfhbclqhu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190320044849/https://core.ac.uk/download/pdf/81185797.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/6f/81/6f813eee02c6cd3914cf0e4d1c3a77fe91368697.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1006/jcss.1998.1569"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

On Generalizing Beyond Domains in Cross-Domain Continual Learning [article]

Christian Simon, Masoud Faraki, Yi-Hsuan Tsai, Xiang Yu, Samuel Schulter, Yumin Suh, Mehrtash Harandi, Manmohan Chandraker
<span title="2022-03-08">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we consider a more realistic scenario of continual learning under domain shifts where the model must generalize its inference to an unseen domain.  ...  In addition, we propose an approach based on the exponential moving average of the parameters for better knowledge distillation.  ...  Furthermore, let f φ : H → Y be a classifier network parametrized by φ that maps the outputs of f θ to class label values.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.03970v1">arXiv:2203.03970v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ertyqrvcr5fnzao6ktyssi2bwi">fatcat:ertyqrvcr5fnzao6ktyssi2bwi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220515025710/https://arxiv.org/pdf/2203.03970v1.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/f7/70f776a2566be51c31109cbf152e9d45c91aade0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.03970v1" 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>

Page 4521 of Mathematical Reviews Vol. , Issue 97G [page]

<span title="">1997</span> <i title="American Mathematical Society"> <a target="_blank" rel="noopener" href="https://archive.org/details/pub_mathematical-reviews" style="color: black;">Mathematical Reviews </a> </i> &nbsp;
The optimal asymptotic rate of learning for a more restricted case, namely for parametric classes of models with & free param- eters, had already been evaluated previously by Rissanen [IEEE Trans.  ...  Summary: “Recurrent perceptron classifiers generalize the usual perceptron model.  ... 
<span class="external-identifiers"> </span>
<a target="_blank" rel="noopener" href="https://archive.org/details/sim_mathematical-reviews_1997-07_97g/page/4521" title="read fulltext microfilm" 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> Archive [Microfilm] <div class="menu fulltext-thumbnail"> <img src="https://archive.org/serve/sim_mathematical-reviews_1997-07_97g/__ia_thumb.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a>

Budget Learning via Bracketing [article]

Aditya Gangrade, Durmus Alp Emre Acar, Venkatesh Saligrama
<span title="2020-04-14">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a new formulation for the BL problem via the concept of bracketings.  ...  We explore theoretical aspects of this formulation, providing PAC-style learnability definitions; associating the notion of budget learnability to approximability via brackets; and giving VC-theoretic  ...  This work was supported partly by the National Science Foundation Grant 1527618, the Office of Naval Research Grant N0014-18-1-2257 and by a gift from the ARM corporation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.06298v1">arXiv:2004.06298v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5nlhj4mhj5dxvfwzlzzeq7lsmq">fatcat:5nlhj4mhj5dxvfwzlzzeq7lsmq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200416032704/https://arxiv.org/pdf/2004.06298v1.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/05/07/05077ad6d33b72ce24a1cb86b880190a4c546e6d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.06298v1" 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 Recognize Three-Dimensional Objects

Dan Roth, Ming-Hsuan Yang, Narendra Ahuja
<span title="">2002</span> <i title="MIT Press - Journals"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rckx6fqoszfvva5c53bqivu5am" style="color: black;">Neural Computation</a> </i> &nbsp;
A learning account for the problem of object recognition is developed within the probably approximately correct (PAC) model of learnability.  ...  We show that these properties can be exploited to yield an efficient learning approach in terms of sample and computational complexity within the PAC model.  ...  Based on these assumptions, this work provides a learning theory account for the problem of object recognition within the PAC model of learnability.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/089976602753633394">doi:10.1162/089976602753633394</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/11972908">pmid:11972908</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rsbqcx2h35fj5ecqgnuvznvfrm">fatcat:rsbqcx2h35fj5ecqgnuvznvfrm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170707010306/http://vision.ai.illinois.edu/publications/Learning_Recognize_Neural_Computation_2002.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/8c/b3/8cb351c84854e83747d1ba2e9f44e85b13398cde.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/089976602753633394"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> mitpressjournals.org </button> </a>

Black-box Certification and Learning under Adversarial Perturbations [article]

Hassan Ashtiani, Vinayak Pathak, Ruth Urner
<span title="2022-02-22">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We analyze a PAC-type framework of semi-supervised learning and identify possibility and impossibility results for proper learning of VC-classes in this setting.  ...  We formally study the problem of classification under adversarial perturbations from a learner's perspective as well as a third-party who aims at certifying the robustness of a given black-box classifier  ...  Acknowledgements We thank the Vector Institute for providing us with the meeting space in which this work was developed! Ruth Urner and Hassan Ashtiani were supported by NSERC Discovery Grants.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.16520v2">arXiv:2006.16520v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zbbxo3rimzfanoaqzok75ovpbe">fatcat:zbbxo3rimzfanoaqzok75ovpbe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200713190909/https://arxiv.org/pdf/2006.16520v1.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/2006.16520v2" 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>

PAC-Bayesian Generalisation Error Bounds for Gaussian Process Classification

Matthias Seeger, Peter Bartlett
<span title="">2003</span> <i title="Test accounts"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jknrc7cg5zdmzoiaibuemsqpfu" style="color: black;">Journal of machine learning research</a> </i> &nbsp;
In this paper, by applying the PAC-Bayesian theorem of McAllester (1999a), we prove distributionfree generalisation error bounds for a wide range of approximate Bayesian GP classification techniques.  ...  We also provide a new and much simplified proof for this powerful theorem, making use of the concept of convex duality which is a backbone of many machine learning techniques.  ...  Furthermore, we think that the general PAC-Bayesian theorem can be rather straightforwardly applied to a host of approximate Bayesian schemes for parametric models (see also Langford and Caruana, 2002  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/153244303765208386">doi:10.1162/153244303765208386</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/apqdzkzodjfwphsfjbm7mcw3ge">fatcat:apqdzkzodjfwphsfjbm7mcw3ge</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20030830070257/http://www.dai.ed.ac.uk:80/homes/seeger/papers/pacbgp-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/e5/24/e5249faa1b2802fe7dda735bb54008d5deb948cd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/153244303765208386"> <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>

Model-Based Domain Generalization [article]

Alexander Robey and George J. Pappas and Hamed Hassani
<span title="2021-11-15">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
, and PACS.  ...  We show that under a natural model of data generation and a concomitant invariance condition, the domain generalization problem is equivalent to an infinite-dimensional constrained statistical learning  ...  In particular, recall the following definition of agnostic PAC learnability: Definition A.5 (PAC learnability).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.11436v5">arXiv:2102.11436v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vsl7jcofe5dw3jndbtvuph24cu">fatcat:vsl7jcofe5dw3jndbtvuph24cu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211122203420/https://arxiv.org/pdf/2102.11436v5.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/69/3d/693d3fd92c6cf825cfe988cb32cf92e733d6230a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.11436v5" 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>

Maximum Margin Algorithms with Boolean Kernels [chapter]

Roni Khardon, Rocco A. Servedio
<span title="">2003</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
We show that maximum margin algorithms using the Boolean kernels do not PAC learn t(n)term DNF for any t(n) = ω(1), even when used with such a SRM scheme.  ...  This motivates the question of whether maximum margin algorithms such as Support Vector Machines can learn Disjunctive Normal Form expressions in the Probably Approximately Correct (PAC) learning model  ...  easier than online mistake bound learning (it is well known that any concept class which is efficiently learnable in the mistake bound model is efficiently PAC learnable, but the converse is not true  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-45167-9_8">doi:10.1007/978-3-540-45167-9_8</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hwapwcrdufbjrgeguw2i6hunp4">fatcat:hwapwcrdufbjrgeguw2i6hunp4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20110102055836/http://jmlr.csail.mit.edu/papers/volume6/khardon05a/khardon05a.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/52/8d/528d2f1d6750bd70b53d3f759d301d8d79b27481.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-45167-9_8"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Viewpoint: Boosting Recessions

Serena Ng
<span title="2014-01-27">2014</span> <i title="Wiley"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/odmctap4anhjzp5pmgazhmpks4" style="color: black;">Canadian Journal of Economics</a> </i> &nbsp;
There is a distinct difference in the size and composition of the relevant predictor set before and after mid-1980.  ...  Warning signals for the post-1990 recessions have been sporadic and easy to miss. The results underscore the challenge that changing characteristics of business cycles pose for predicting recessions.  ...  Given covariates x and outcome y, a problem is said to be strongly PAC learnable if there exists a classifier (or learner) f (x) such that the error rate ERROR = E[1(f (x) = y] is arbitrarily small.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1111/caje.12070">doi:10.1111/caje.12070</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lqhmki3axvefffdt4detxpz2ya">fatcat:lqhmki3axvefffdt4detxpz2ya</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170706050643/http://www.columbia.edu/~sn2294/pub/cje2014.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/a4/b4a482c989fe16ec18e5e42b4588a1ba63357b02.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1111/caje.12070"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

A Brief Introduction to Machine Learning for Engineers [article]

Osvaldo Simeone
<span title="2018-05-17">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This monograph is meant as an entry point for researchers with a background in probability and linear algebra.  ...  The treatment concentrates on probabilistic models for supervised and unsupervised learning problems.  ...  PAC Learnability for Finite Hypothesis Classes In this section, we consider models with a finite number of hypotheses.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.02840v3">arXiv:1709.02840v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4ivew7im6ndyhgzdymval3jh2m">fatcat:4ivew7im6ndyhgzdymval3jh2m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200911145745/https://arxiv.org/pdf/1709.02840v3.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/76/9d/769d3ae8b772902587c55dee471b2fb5808aabdd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.02840v3" 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>

The VC dimension of constraint-based grammars

Max Bane, Jason Riggle, Morgan Sonderegger
<span title="">2010</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/w3dtv5pijzaano7z4qblgomjtq" style="color: black;">Lingua</a> </i> &nbsp;
This establishes a fundamental bound on the complexity of HG in terms of its capacity to classify sets of linguistic data that has significant ramifications for learnability.  ...  set of constrains is a linear function of k.  ...  Acknowledgments For useful discussion of this work and insightful comments on earlier drafts, we are grateful to Giorgio Magri, Partha Niyogi, Joe Pater, Chris Potts, and two anonymous Lingua reviewers  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.lingua.2009.07.001">doi:10.1016/j.lingua.2009.07.001</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nx4ryokfa5b4xajx7rfcpujaz4">fatcat:nx4ryokfa5b4xajx7rfcpujaz4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170812115803/http://clml.uchicago.edu/~max/hgvcd.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/8f/e1/8fe19d1c81148a98bbd97313f31c0c52f146d331.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.lingua.2009.07.001"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 217 results