Filters








349,966 Hits in 5.7 sec

Program size restrictions in computational learning

Sanjay Jain, Arun Sharma
1994 Theoretical Computer Science  
Sharma, Program size restrictions in computational learning, Theoretical Computer Science 127 (1994) 351-386.  ...  All rights reserved SSDI 0304-3975(93)E0088-L 3 These motivations for succinctness in language learning are based on discussions with John Case. Program size restrictions in computational learning 355  ...  Program size restrictions in computational learning  ... 
doi:10.1016/0304-3975(94)90047-7 fatcat:gkwmnsnixrfk3eb2jqu6f3fkuq

Strategy Learning for Reasoning Agents [chapter]

Hendrik Skubch, Michael Thielscher
2005 Lecture Notes in Computer Science  
We show how a learning agent can exploit background knowledge of its actions and environment in order to restrict the hypothesis space, which enables the learning of complex logic program clauses.  ...  Using techniques of inductive logic programming, strategies are learned in two steps: A given example set is first generalized into an overly general theory, which then gets refined.  ...  In this paper, we present a method to learn strategy programs from examples using Inductive Logic Programming (ILP).  ... 
doi:10.1007/11564096_75 fatcat:nba6jutpjnawdjdhznnxw56kdq

Discovering optimization algorithms through automated learning [chapter]

Eric Breimer, Mark Goldberg, David Hollinger, Darren Lim
2007 DIMACS Series in Discrete Mathematics and Theoretical Computer Science  
In this paper, we describe the supervised learning approach to optimization problems in the spirit of the PAC learning model.  ...  We describe examples of learning backtracking-based algorithms and algorithms that implement the dynamic programming paradigm.  ...  One of the most transparent restrictions on inputs used for testing is their sizes.  ... 
doi:10.1090/dimacs/069/02 dblp:conf/dimacs/BreimerGHL01 fatcat:6cfqh23pjfgqxalbyl4twzxvdu

Machine Induction without Revolutionary Changes in Hypothesis Size

John Case, Sanjay Jain, Arun Sharma
1996 Information and Computation  
with no size constraint, an unbounded, finite number of anomalies in the final program, but with no more than i mind changes.  ...  Allowing up to one extra bounded size mind change towards a final program learned certainly does not appear revolutionary.  ...  We are also grateful to the referee for many helpful suggestions, and especially for pointing out the investigation of machine induction without paradigm shifts in the context of non-standard programming  ... 
doi:10.1006/inco.1996.0064 fatcat:ffqdzimp7vczniq4rfutrfwrke

Preface

H. Arimura, S. Jain
2005 Theoretical Computer Science  
queries in terms of the DNS size and CNF size of a target relation.  ...  Acyclicity is a natural concept in hypergraph theory, and proved to be effective to restrict the computational complexity of many combinatorial problems in database area.  ... 
doi:10.1016/j.tcs.2005.09.002 fatcat:jtfdzdc2o5hf3c65clujc66itm

Page 4911 of Mathematical Reviews Vol. , Issue 95h [page]

1995 Mathematical Reviews  
We show and exploit as a tool the desirable property that the learning power under our size- restricted criteria (for successful learning) is independent of the underlying acceptable programming systems  ...  In this paper we study some of the trade-offs in learning power involved in making a well-defined version of this restriction.  ... 

Training Large Scale Deep Neural Networks on the Intel Xeon Phi Many-Core Coprocessor

Lei Jin, Zhaokang Wang, Rong Gu, Chunfeng Yuan, Yihua Huang
2014 2014 IEEE International Parallel & Distributed Processing Symposium Workshops  
The sequential deep learning algorithms usually can not finish the computation in an acceptable time.  ...  and Restricted Boltzmann Machine (RBM).  ...  ACKNOWLEDGMENT This work is funded in part by China NSF Grants (No. 61223003), and the USA Intel Labs University Resea rch Program.  ... 
doi:10.1109/ipdpsw.2014.194 dblp:conf/ipps/JinWGYH14 fatcat:tpmcupt4indklfoj3dtwm65rze

On learning width two branching programs (extended abstract)

Nader H. Bshouty, Christino Tamon, David K. Wilson
1996 Proceedings of the ninth annual conference on Computational learning theory - COLT '96  
We also observe that PAC learning monotone width two branching programs (which are width two branching programs with exactly one rejecting sink) is as hard as learning DNF formulae.  ...  We prove that strict width two branching programs or ¢ ¤ £ ¦ ¥ (which are width two branching programs with exactly two sinks, as defined in [BDFP86]) are properly PAC learnable under any distribution.  ...  Clearly, a polynomial-sized DNF formula can be computed by a monotone width two branching program with a polynomial number of nodes.  ... 
doi:10.1145/238061.238102 dblp:conf/colt/BshoutyTW96 fatcat:3umxsrclsrglve74vkgqkgitai

Page 388 of Behavior Research Methods Vol. 8, Issue 4 [page]

1976 Behavior Research Methods  
The program uses FORTRAN IV. Standard input/output procedures are utilized. Computer. The computer used is an XDS Sigma 6 with 40K words (160K bytes) of core memory. Restrictions.  ...  Learning is organized by chunking. Journal of Verbal learning and Verbal Behavior, 1976, in press. Pellegrino, J. W.  ... 

An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints [article]

Zhe Li, Xuehan Xiong, Zhou Ren, Ning Zhang, Xiaoyu Wang, Tianbao Yang
2018 arXiv   pre-print
The challenge in designing such programs lies in how to balance between large search space of the network structures and high computational costs.  ...  In this paper, we study how to design a genetic programming approach for optimizing the structure of a CNN for a given task under limited computational resources yet without imposing strong restrictions  ...  A great challenge size of search space computational costs Real et al. 2017 (94%, 10 4 in solving these issues lies in how to balance the trade-off between the size of search space and the computational  ... 
arXiv:1806.00851v1 fatcat:skbwddtvonhkfkihpjhzyyyrk4

Developing Applications On-Board of Robots with Becerik

Bora İ. Kumova, Savaş Takan
2011 Advanced Materials Research  
For instance, children who have not learned using a computer yet and who develop their robot applications while playing.  ...  Or for instance in the robots' operating environment, where there is no computer available.  ...  Introduction State-of-the-art in robot programming is that robot applications are first developed on a computer, thereafter loaded to the robot, where they cannot be changed any more.  ... 
doi:10.4028/www.scientific.net/amr.403-408.4689 fatcat:zf5bbkcxtzazrjt7yl2fecpoju

DIGICALC: a restriction fragment analysis program

Armand MacMurray
1986 Nucleic Acids Research  
of modification, and (iv) improved functionality in sizing and comparing restriction fragments over manual methods.  ...  DIGICALC is a program designed to aid in the acquisition, storage, and analysis of nucleic acid restriction fragment data.  ...  In a typical program session, one enters data from one or more blots, calculates the band sizes, and then produces a table showing the restriction fragment sizes for each DNA sample. Key Features.  ... 
doi:10.1093/nar/14.1.529 pmid:3003681 pmcid:PMC339437 fatcat:y6tlt4mz6rcwfig64eqs5yez64

Page 9198 of Mathematical Reviews Vol. , Issue 2004k [page]

2004 Mathematical Reviews  
l<\I"ll) and the size of its constraints is polynomial in the size of &,t.  ...  in the number of states and exponen- tial in the size of the constraints.  ... 

Syntax-guided synthesis

Rajeev Alur, Rastislav Bodik, Garvit Juniwal, Milo M. K. Martin, Mukund Raghothaman, Sanjit A. Seshia, Rishabh Singh, Armando Solar-Lezama, Emina Torlak, Abhishek Udupa
2013 2013 Formal Methods in Computer-Aided Design  
Our goal is to identify the core computational problem common to these proposals in a logical framework.  ...  The computational problem then is to find an implementation from the set of candidate expressions so that it satisfies the specification in the given theory.  ...  This research is supported by the NSF Expeditions in Computing project ExCAPE (award CCF 1138996).  ... 
doi:10.1109/fmcad.2013.6679385 fatcat:mcbbl2b3yfgchcam4zsdfnsy4a

Learning Restricted Models of Arithmetic Circuits

Adam R. Klivans, Amir Shpilka
2006 Theory of Computing  
As a consequence, we obtain polynomial-time algorithms for learning restricted algebraic branching programs as well as noncommutative set-multilinear arithmetic formulae.  ...  We present a polynomial time algorithm for learning a large class of algebraic models of computation.  ...  Acknowledgments We thank Ran Raz for many helpful discussions in all stages of this work. We also thank Eli Ben-Sasson for important conversations at an early stage of this research.  ... 
doi:10.4086/toc.2006.v002a010 dblp:journals/toc/KlivansS06 fatcat:6ddt4sw6g5c7bdy2b3cqnultx4
« Previous Showing results 1 — 15 out of 349,966 results