Filters








109,800 Hits in 6.9 sec

Page 3069 of Mathematical Reviews Vol. , Issue 96e [page]

1996 Mathematical Reviews  
68T0S Bshouty, Nader H. (3-CALG; Calgary, AB); Hancock, Thomas R.; Hellerstein, Lisa (1-NW-E; Evanston, IL) Learning Boolean read-once formulas over generalized bases.  ...  algorithm for read-once formulas over the union of B and the arbitrary func- tions of constant fan-in.  ... 

Page 4355 of Mathematical Reviews Vol. , Issue 96g [page]

1996 Mathematical Reviews  
We present polynomial time algorithms for exact learning of arith- metic read-once formulas over a field.  ...  We also show the existence of nonuniform deterministic membership query algorithms for arbitrary read- once formulas over fields of characteristic 0, and division-free read-once formulas over fields that  ... 

Learning arithmetic read-once formulas

Nader H. Bshouty, Thomas R. Hancock, Lisa Hellerstein
1992 Proceedings of the twenty-fourth annual ACM symposium on Theory of computing - STOC '92  
We present polynomial time algorithms for exact learning of arithmetic read-once formulas over a field.  ...  We also show the existence of nonuniform deterministic membership query algorithms for arbitrary read-once formulas over fields of characteristic 0, and division-free read-once formulas over fields that  ...  It can be easily shown that this formula is read-once and the unary operation attached to each variable xi is A'--(ali-(i)) ( ) ( Acknowledgments.  ... 
doi:10.1145/129712.129747 dblp:conf/stoc/BshoutyHH92 fatcat:7yaukevsprafddh3kyg3p7yhp4

Learning Arithmetic Read-Once Formulas

Nader H. Bshouty, Thomas R. Hancock, Lisa Hellerstein
1995 SIAM journal on computing (Print)  
We present polynomial time algorithms for exact learning of arithmetic read-once formulas over a field.  ...  We also show the existence of nonuniform deterministic membership query algorithms for arbitrary read-once formulas over fields of characteristic 0, and division-free read-once formulas over fields that  ...  It can be easily shown that this formula is read-once and the unary operation attached to each variable xi is A'--(ali-(i)) ( ) ( Acknowledgments.  ... 
doi:10.1137/s009753979223664x fatcat:uhishjsdprbvxf4xfnrldt7tge

A Guide to Learning Arithmetic Circuits

Ilya Volkovich
2016 Annual Conference Computational Learning Theory  
In particular, we show that: • Efficient learning algorithms for arithmetic circuit classes imply explicit exponential lower bounds. • General circuits and formulas can be learned efficiently with membership  ...  In this paper, we exhibit several connections between learning algorithms for arithmetic circuits and other problems.  ...  The author would also like to thank Michael Forbes and Rocco Servedio for useful conversations.  ... 
dblp:conf/colt/Volkovich16 fatcat:33mwk4ta4rbj5pngellfkjwjdu

Computational learning theory

Dana Angluin
1992 Proceedings of the twenty-fourth annual ACM symposium on Theory of computing - STOC '92  
Hancock and L. Hellerstein. Learning read- once formulas over fields and extended bases. In Proceedings of the Fourth Annual Workshop on Computational Learning Theory, pages 326-336.  ...  Hancock and Hellerstein [55] give polynomial al- gorithms using membership and equivalence queries that exactly identify read-once formulas over extended bases and fields.  ... 
doi:10.1145/129712.129746 dblp:conf/stoc/Angluin92 fatcat:7aw3cnd745bellyhu7phywpul4

On the learnability of Zn-DNF formulas (extended abstract)

Nader H. Bshouty, Zhixiang Chen, Scott E. Decatur, Steven Homer
1995 Proceedings of the eighth annual conference on Computational learning theory - COLT '95  
Although many learning problems can be reduced to learning Boolean functions, in many  ...  Those classes are diagonal .ZN-terms and binary weighted read-once Z'N-terms.  ...  [AHK93]) that read-once Boolean functions over the basis (AND, OR, NOT) are poly- nomial time learnable with equivalence and member- ship queries.  ... 
doi:10.1145/225298.225322 dblp:conf/colt/BshoutyCDH95 fatcat:hyakjt5uanhtfdoutcko5gqleu

10 Years of Probabilistic Querying – What Next? [chapter]

Martin Theobald, Luc De Raedt, Maximilian Dylla, Angelika Kimmig, Iris Miliaraki
2013 Lecture Notes in Computer Science  
techniques based on knowledge compilation and lifted (first-order) inference.  ...  , which all calls for a more intensive study of the commonalities and integration of the two fields.  ...  of evaluating different query structures such as safe plans or read-once formulas.  ... 
doi:10.1007/978-3-642-40683-6_1 fatcat:lofuquzqgbb4hcjtjeqydyakbe

Exact learning of linear combinations of monotone terms from function value queries

Atsuyoshi Nakamura, Naoki Abe
1995 Theoretical Computer Science  
These bounds are shown by generalizing Roth and Benedek's technique for analyzing the learning problem for k-sparse multivariate polynomials over GF(2) (Roth and Benedek, 1991) to those over an arbitrary  ...  formula.  ...  Santa Cruz and Prof. Lisa Hellerstein of Northwestern University for sharing their work on learning GF(2) polynomials with us.  ... 
doi:10.1016/0304-3975(94)00166-g fatcat:tqea46djfzbihgq5vc2stcdlsi

Asking Questions to Minimize Errors

Nader H. Bshouty, Sally A. Goldman, Thomas R. Hancock, Sleiman Matar
1996 Journal of computer and system sciences (Print)  
The classes we consider here are monotone DNF formulas, Horn sentences, O(log n)-term DNF formulas, read-k sat-j DNF formulas, readonce formulas over various bases, and deterministic finite automata.  ...  As an example, consider the class of DNF formulas over n variables with at most k=O(log n) terms.  ...  Nader Bshouty and Sleiman Matar are supported in part by the NSERC of Canada. Sally Goldman is supported in part by NSF RIA CCR-91110108 and NSF National Young Investigator grant CCR-9357707.  ... 
doi:10.1006/jcss.1996.0021 fatcat:hoes3bhwcnddddhh65rbkfpi2m

Learning probabilistic read-once formulas on product distributions

Robert E. Schapire
1994 Machine Learning  
This paper presents a polynomial-time algorithm for inferring a probabilistic generalization of the class of read-once Boolean formulas over the usual basis {AND, OR, NOT}.  ...  Further, this class of probabilistic formulas includes read-once formulas whose behavior has been corrupted by large amounts of random noise.  ...  I am also grateful to two anonymous referees for their thorough reading and thoughtful suggestions.  ... 
doi:10.1007/bf00993162 fatcat:v2iwhleiwzcpzmryjib3y7ijjy

INTRODUCTION TO THE SPECIAL ISSUE

2020 Studies in Second Language Acquisition  
The study by Pujadas and Muñoz contributes to the area by addressing the effects of captions and subtitles on TV viewing comprehension in a classroom intervention that extends over 8 months, which affords  ...  The study by Puimège and Peters explores the incidental learning of formulaic sequences from audiovisual input and factors affecting the learning of formulaic sequences.  ... 
doi:10.1017/s0272263120000212 fatcat:44zsqmyynfgupn5pbelxmrme3q

Cryptography and machine learning [chapter]

Ronald L. Rivest
1993 Lecture Notes in Computer Science  
This paper gives a survey of the relationship between the fields of cryptography and machine learning, with an emphasis on how each field has contributed ideas and techniques to the other.  ...  Schapire [40] shows how to efficiently infer a class of formula he calls "probabilistic read-once formula" against product distributions.  ...  The reader unfamiliar with either of these fields may wish to consult some of the excellent surveys and texts available for background reading.  ... 
doi:10.1007/3-540-57332-1_36 fatcat:tfi6lrc7jnc5dkan6pjwk4mrii

Design of a Telerobotic Interface System by Using Object Recognition Techniques [chapter]

Raül Marín, Pedro José Sanz, Antonio José Jimeno, Jose Manuel Iñesta
2000 Lecture Notes in Computer Science  
This paper presents a real application that adds learning capabilities to a telerobotic system, designed formerly to manipulate everyday objects over a board.  ...  The user interaction is based on a restricted natural language and object recognition techniques have been designed specifically in order to acquire a system that responds as fast as possible to the user  ...  Once this happens the system is able to recognise samples belonging to that class, and that means the program has learned a new class definition.  ... 
doi:10.1007/3-540-44522-6_86 fatcat:zbjkkyakizdzjgzw7fj3xnph44

Learning counting functions with queries

Zhixiang Chen, Steven Homer
1997 Theoretical Computer Science  
We prove that, for any given integer q > 2, over the domain Zl, the class of read-once disjunctions of Boolean-weighted counting functions with modulus q is polynomial-time learnable with only one equivalence  ...  We investigate the problem of learning disjunctions of counting functions, which are general cases of parity and modulo functions, with equivalence and membership queries.  ...  Acknowledgements We are very grateful to Robert Schapire for valuable discussions on this topic, and especially for providing us with his algorithm for learning disjunctions of parities with equivalence  ... 
doi:10.1016/s0304-3975(96)00144-2 fatcat:nvzyxo3slbc6fgp7nwvyqe374u
« Previous Showing results 1 — 15 out of 109,800 results