Filters








493 Hits in 2.3 sec

PAC Learning of Some Subclasses of Context-Free Grammars with Basic Distributional Properties from Positive Data [chapter]

Chihiro Shibata, Ryo Yoshinaka
<span title="">2013</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;
This paper shows that several subclasses of contextfree languages that are known to be exactly learnable with membership queries by distributional learning techniques are pac learnable from positive data  ...  On the other hand, positive results on the pac learnability of cfls are rather limited and quite weak.  ...  Particularly their target classes are rather small: In fact, some simple finite languages and infinite languages like a + are not covered.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-40935-6_11">doi:10.1007/978-3-642-40935-6_11</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fkr3eznpxvhttei6tl3h7pio5e">fatcat:fkr3eznpxvhttei6tl3h7pio5e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190221031434/http://pdfs.semanticscholar.org/2dca/8229ded510c106b39ea3e051fd6462e266c6.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/2d/ca/2dca8229ded510c106b39ea3e051fd6462e266c6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-40935-6_11"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Learning Stochastic Finite Automata [chapter]

Colin de la Higuera, Jose Oncina
<span title="">2004</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;
Stochastic deterministic finite automata have been introduced and are used in a variety of settings. We report here a number of results concerning the learnability of these finite state machines.  ...  In the setting of identification in the limit with probability one, we prove that stochastic deterministic finite automata cannot be identified from only a polynomial quantity of data.  ...  A class of stochastic languages L is polynomially Pac-learnable in terms of a representation class R (using distance d) if there exists an algorithm φ(·) and a polynomial p() such that for any language  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-30195-0_16">doi:10.1007/978-3-540-30195-0_16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4mlmcctfsvcnnbqnso5v4b6w34">fatcat:4mlmcctfsvcnnbqnso5v4b6w34</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20091211140007/http://grfia.dlsi.ua.es/repositori/grfia/pubs/143/icgi.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/42/9d/429d9dd16fceab3db40c3d544a2a6746eb078a6e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-30195-0_16"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Learning DFA from simple examples [chapter]

Rajesh Parekh, Vasant Honavar
<span title="">1997</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;
Thus, the class C N is exactly learnable with probability greater than 1, under the PACS model. 2 We n o w show that the class of DFA can be identi ed in polynomial time under the PACS model.  ...  We present a framework for learning DFA from simple examples.  ...  examples.Cncept classes such a s l o g n-term DNF and simple k-reversible DFA are PAC learnable with simple examples whereas their PAC learnability in the standard sense is unknown Li & Vit anyi, 1991  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-63577-7_39">doi:10.1007/3-540-63577-7_39</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dqfzeb7hqrfjzd4dm5kfdtb4ma">fatcat:dqfzeb7hqrfjzd4dm5kfdtb4ma</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20050816061031/http://archives.cs.iastate.edu:80/documents/disk0/00/00/01/52/00000152-01/TR97-07.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/b7/a6/b7a68214ef8e441a59f5fa4766da4517eea68b60.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-63577-7_39"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

PAC learning under helpful distributions [chapter]

François Denis, Rémi Gilleron
<span title="">1997</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;
Note that Decision lists and DNF are not known to be learnable in the Goldman and Mathias model. A new simple PAC model, where "simple" refers to Kolmogorov complexity, is introduced.  ...  A PAC teaching model -under helpful distributions -is proposed which introduces the classical ideas of teaching models within the PAC setting: a polynomial-sized teaching set is associated with each target  ...  We will say simple PAC learnable for the simple PAC learning model of Li and Vitányi, PACS learnable for the simple PAC learning model of Denis et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-63577-7_40">doi:10.1007/3-540-63577-7_40</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/csr3on22ejb3bpnpqwtpffzb4a">fatcat:csr3on22ejb3bpnpqwtpffzb4a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190306214218/http://pdfs.semanticscholar.org/ed86/97d09c882e83903bf01bd446e850bee39643.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/86/ed8697d09c882e83903bf01bd446e850bee39643.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-63577-7_40"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Computational learning theory

Dana Angluin
<span title="">1992</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jlc5kugafjg4dl7ozagimqfcbm" style="color: black;">Proceedings of the twenty-fourth annual ACM symposium on Theory of computing - STOC &#39;92</a> </i> &nbsp;
Jerrum [71] similarly shows that a simple class of formulae invariant under cyclic shifts of the variables is not properly PAC-learnable.  ...  a PAC-learning al- gorithm for C in terms of l-l with membership queries. 11.2 Automata and formal languages Angluin [8] gives a polynomial-time algorithm for learn- ing deterministic finite  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/129712.129746">doi:10.1145/129712.129746</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/stoc/Angluin92.html">dblp:conf/stoc/Angluin92</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7aw3cnd745bellyhu7phywpul4">fatcat:7aw3cnd745bellyhu7phywpul4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809114332/http://www2.denizyuret.com/ref/angluin/coltsurvey.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/98/99/9899c9d7f3a5b5d9fc918675c0843754d160c986.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/129712.129746"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Some Classes of Regular Languages Identifiable in the Limit from Positive Data [chapter]

François Denis, Aurélien Lemay, Alain Terlutte
<span title="">2002</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;
Attribute Grammars with Structured Data for Natural Language Processing p. 237 A PAC Learnability of Simple Deterministic Languages p. 249 On the Learnability of Hidden Markov Models p. 261 Shallow  ...  for Inductive Learning of Typed-Unification Grammars p. 299 A Tool for Language Learning Based on Categorial Grammars and Semantic Information p. 303 'NAIL': Artificial Intelligence Software for  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-45790-9_6">doi:10.1007/3-540-45790-9_6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nmlknwqoyfbybhb6rpomqrn7qy">fatcat:nmlknwqoyfbybhb6rpomqrn7qy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190219181927/http://pdfs.semanticscholar.org/1c9e/a28d3bdf648ddbda05c6c9fc7ff7e908444b.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/1c/9e/1c9ea28d3bdf648ddbda05c6c9fc7ff7e908444b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-45790-9_6"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

The learnability of description logics with equality constraints

William W. Cohen, Haym Hirsh
<span title="">1994</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/h4nnd7sxwzcwhetu5qkjbcdh6u" style="color: black;">Machine Learning</a> </i> &nbsp;
In summary, previous analyses in the pac-model have focused primarily on subsets of Prolog, and have discovered only a few highly restricted first-order languages that are learnable.  ...  Most previous analyses in the pac-model have focused on subsets of Prolog, and only a few highly restricted subsets have been shown to be learnable.  ...  The authors would like to thank Rob Schapire and Mike Kearns for comments on a draft of the paper, and Alex Borgida for comments on early version of some of the proofs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/bf00993470">doi:10.1007/bf00993470</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cz3o3setafh65iu27urlf7zdtm">fatcat:cz3o3setafh65iu27urlf7zdtm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170911212424/https://link.springer.com/content/pdf/10.1007%2FBF00993470.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/61/2d/612d577534dbbf546405d4036d912666523a8164.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/bf00993470"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Introduction: Special issue on computational learning theory

Leonard Pitt
<span title="">1990</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/h4nnd7sxwzcwhetu5qkjbcdh6u" style="color: black;">Machine Learning</a> </i> &nbsp;
The class of simple deterministic languages is a proper subclass of the context-free languages that properly includes the regular languages.  ...  He shows that there is a polynomialtime learning algorithm for the class of simple deterministic grammars using equivalence and membership queries?  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/bf00116033">doi:10.1007/bf00116033</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mmmzufflubhilb4aeset6yhyke">fatcat:mmmzufflubhilb4aeset6yhyke</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180730002610/https://link.springer.com/content/pdf/10.1007%2FBF00116033.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/5f/37/5f3779af15d8ef25062c95e9159ed8153069ef52.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/bf00116033"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

On the Learnability of Shuffle Ideals [chapter]

Dana Angluin, James Aspnes, Aryeh Kontorovich
<span title="">2012</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;
Somewhat surprisingly, we discovered that even a class as simple as the shuffle ideals is not properly PAC learnable, unless RP=NP.  ...  Although PAC learning unrestricted regular languages is long known to be a very difficult problem, one might suppose the existence (and even an abundance) of natural efficiently learnable sub-families.  ...  Acknowledgments We thank Sarah Eisenstat for the construction reducing the alphabet size to 3 in the proof of Theorem 4 and the anonymous referees for their helpful comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-34106-9_12">doi:10.1007/978-3-642-34106-9_12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wr55gysfkzg3redp2if5275hwe">fatcat:wr55gysfkzg3redp2if5275hwe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20121114193438/http://www.cs.yale.edu/homes/aspnes/papers/alt2012-proceedings.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/b8/58/b8583bdc109bf2c28ec7351361e53be99ce0026b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-34106-9_12"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Polynomial Time Learnability of a Sub-class of Linear Languages

Yasuhiro Tajima, Yoshiyuki Kotani, Matsuaki Terada
<span title="">2005</span> <i title="Information Processing Society of Japan"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q4v5dbr74zb7rih5ti465f6yba" style="color: black;">IPSJ Digital Courier</a> </i> &nbsp;
We propose some PAC like settings for a learning problem of a sub-class of linear languages, and show its polynomial time learnability in each of our settings.  ...  Here, the sub-class of linear languages is newly defined, and it includes the class of regular languages and the class of even linear languages.  ...  Acknowledgments This research report is partially supported by Grant-in-Aid for Young Scientists, No.16700007 to the first author from the Ministry of Education, Culture, Sports, Science and Technology  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2197/ipsjdc.1.643">doi:10.2197/ipsjdc.1.643</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ryigcjshqngspftt7cqt4qnxwy">fatcat:ryigcjshqngspftt7cqt4qnxwy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20181031045220/https://www.jstage.jst.go.jp/article/ipsjdc/1/0/1_0_643/_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/47/cb/47cb9ef148291246148e238814bc1ffc5d2a9b82.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2197/ipsjdc.1.643"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Bayesian Inductive Logic Programming [chapter]

Stephen Muggleton
<span title="">1994</span> <i title="Elsevier"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/v54jrmjbpzgodi4buoyaj7vrzm" style="color: black;">Machine Learning Proceedings 1994</a> </i> &nbsp;
It is argued that U-learnability is more appropriate than PAC for Universal (Turing computable) languages.  ...  Incorporation of Bayesian prior distributions over time-bounded hypotheses in PAC leads to a new model called U-learnability.  ...  The author is also supported by a Research Fellowship at Wolfson College, Oxford.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/b978-1-55860-335-6.50052-0">doi:10.1016/b978-1-55860-335-6.50052-0</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icml/Muggleton94.html">dblp:conf/icml/Muggleton94</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/55iza3henjff7bdeqvprl7txue">fatcat:55iza3henjff7bdeqvprl7txue</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20070417144529/http://www.doc.ic.ac.uk/~shm/Papers/bayesian.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/72/14/7214bfbc9c5c0af06cbd445bf06ce6abf04adc34.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/b978-1-55860-335-6.50052-0"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

The Consistency Dimension and Distribution-Dependent Learning from Queries (Extended Abstract) [chapter]

José L. Balcázar, Jorge Castro, David Guijarro, Hans-Ulrich Simon
<span title="">1999</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 prove a new combinatorial characterization of polynomial learnability from equivalence queries, and state some of its consequences relating the learnability of a class with the learnability via equivalence  ...  Then we propose and study two models of query learning in which there is a probability distribution on the instance space, both as an application of the tools developed from the combinatorial characterization  ...  We de ne next the class of simple reversible languages. Li and Vit anyi showed in 8] that this class is learnable in their simple-PAC model.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-46769-6_7">doi:10.1007/3-540-46769-6_7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kps36oqapvdmpc6t5rwyrugara">fatcat:kps36oqapvdmpc6t5rwyrugara</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190307072148/http://pdfs.semanticscholar.org/dcd4/c117cc11053c1f0e9b8e46093df36db37ad4.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/dc/d4/dcd4c117cc11053c1f0e9b8e46093df36db37ad4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-46769-6_7"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Page 7293 of Mathematical Reviews Vol. , Issue 98K [page]

<span title="">1998</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;
In the case of language learning from text, each collection of recursive languages identifiable from text with probability p > 2/3 is deterministically identifiable.  ...  A simple encoding of all possible leaf values will work provided that the size of C is reasonable.  ... 
<span class="external-identifiers"> </span>
<a target="_blank" rel="noopener" href="https://archive.org/details/sim_mathematical-reviews_1998-11_98k/page/7293" 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_1998-11_98k/__ia_thumb.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a>

Some lower bounds for the computational complexity of inductive logic programming [chapter]

Jörg-Uwe Kietz
<span title="">1993</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;
This also shows, that these Hornclauses are not PAC-learnable, unless RP = NP = PSPACE.  ...  Recently, some positive results concerning the learnability of restricted logic programs have been published.  ...  Recently, it has been proven [3] that a k-disjunction of function-free nonrecursive /j-determinate Hornclauses is PAC-learnable under simple distributions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-56602-3_131">doi:10.1007/3-540-56602-3_131</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xy7tdawznrgcpd6rstv33fp3aa">fatcat:xy7tdawznrgcpd6rstv33fp3aa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190220145344/http://pdfs.semanticscholar.org/2523/97a7bda0fbbfc4c044f0402740caf91e0f97.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/25/23/252397a7bda0fbbfc4c044f0402740caf91e0f97.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-56602-3_131"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Page 575 of Mathematical Reviews Vol. , Issue 97A [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;
As corollaries, we obtain the polynomial-time PAC-learnability and the polynomial- time predictability of TP* when membership queries are available.  ...  Summary: “In the PAC-learning, or the query learning model, it has been an important open problem to decide whether the class of DNF and CNF formulas is learnable.  ... 
<span class="external-identifiers"> </span>
<a target="_blank" rel="noopener" href="https://archive.org/details/sim_mathematical-reviews_1997-01_97a/page/575" 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_1997-01_97a/__ia_thumb.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 493 results