Martin Anthony  Home/Search
Context Related
| berkeley.edu/pub/ai/jagota/vol1_1.ps learningtheory.org/article...probANN.ps Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: i.kyushuu.ac.jp/~thoma...surveys (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: There are a number of mathematical approaches to the study of learning and generalization in artificial neural networks. Here we survey the `probably approximately correct' (PAC) model of learning and some of its variants. These models provide a probabilistic framework for the discussion of generalization and learning. This survey concentrates on the sample complexity questions in these models; that is, the emphasis is on how many examples should be used for training. Computational complexity... (Update)
Context of citations to this paper: More
...required to represent a given class of functions. A number of useful theorems regarding VC dimensions are presented in (Anthony, 1994). The limiting cases of the relationship between the function computed and the required dimensionality can be illustrated by giving...
.... An overview of these various dimensions, some details of their history, and some examples of their computation can be found in [5]. In the present work, we view the class F as being induced by an operator T k depending on some kernel function k. Thus F is the image of a...
Cited by: More
Entropy Numbers, Operators and Support Vector Kernels - Williamson, Smola, Schölkopf (1999) (Correct)
Generalization Ability of Folding Networks - Hammer (Correct)
The Loading Problem for Pyramidal Neural Networks - de Souto, de Oliveira (Correct)
Similar documents (at the sentence level):
12.1%: Probabilistic Learning Theory, with Emphasis on Sample Complexity - Anthony (Correct)
6.3%: Computational Learning Theory for Artificial Neural Networks - Anthony, Biggs (1993) (Correct)
Active bibliography (related documents): More All
7.4: Probabilistic Analysis of Learning in Artificial Neural Networks: .. - Anthony (1994) (Correct)
0.8: Lower Bounds on the VC-Dimension of Smoothly Parametrized.. - Wee Sun (Correct)
0.8: Valid Generalisation from Approximate Interpolation - Anthony, Bartlett, al. (1996) (Correct)
Similar documents based on text: More All
0.1: Boolean Functions and Artificial Neural Networks - Martin Anthony Department (Correct)
0.1: Links between Learning and Optimization: a Brief Tutorial - Anthony (2003) (Correct)
0.1: The Sample Complexity and Computational - Complexity Of Boolean (Correct)
Related documents from co-citation: More All
6: Entropy and (context) - Prosser, -- - 1966
6: Scale-sensitive dimensions (context) - Alon, Ben-David et al. - 1993
5: Theoretical Foundations of the Potential Function Method in Pattern Recognition .. (context) - Aizerman, Braverman et al. - 1964
BibTeX entry: (Update)
M. Anthony. Probabilistic analysis of learning in artificial neural networks: The PAC model and its variants. Neural Computing Surveys, 1:1--47, 1997. http://www.icsi.berkeley.edu/~jagota/NCS. http://citeseer.ist.psu.edu/article/anthony97probabilistic.html More
@techreport{ anthony94probabilistic,
author = "Martin Anthony",
title = "Probabilistic Analysis of Learning in Artificial Neural Networks: The {PAC} Model and its Variants",
number = "NC-TR-94-3",
address = "London, UK",
year = "1994",
url = "citeseer.ist.psu.edu/article/anthony97probabilistic.html" }
Citations (may not include all citations):3972 Introduction to Algorithms (context) - Cormen, Leiserson et al. - 1990 ACM
1291 The Nature of Statistical Learning Theory (context) - Vapnik - 1995 ACM
1056 Introduction to the Theory of Neural Computation (context) - Hertz, Krogh et al. - 1991 ACM
537 A theory of the learnable (context) - Valiant - 1984 ACM DBLP
465 Learnability and the VapnikChervonenkis dimension (context) - Blumer, Ehrenfeucht et al. - 1989
454 the uniform convergence of relative frequencies of events to.. (context) - Vapnik, Chervonenkis - 1971
441 Queries and concept learning (context) - Angluin - 1988 ACM DBLP
375 Probability inequalities for sums of bounded random variable.. (context) - Hoeffding - 1963
348 Estimation of Dependences Based on Empirical Data (context) - Vapnik - 1982
318 Convergence of Stochastic Processes (context) - Pollard - 1984
296 A Probabilistic Theory of Pattern Recognition (context) - Devroye, Gyorfi et al. - 1996
273 The strength of weak learnability - Schapire - 1990 ACM DBLP
268 Decision theoretic generalizations of the PAC model for neur.. (context) - Haussler - 1992 ACM DBLP
248 Introduction to Computational Learning Theory (context) - Kearns, Vazirani - 1995
203 What size net gives valid generalization (context) - Baum, Haussler - 1989
184 Cryptographic limitations on learning Boolean formulae and f.. - Kearns, Valiant - 1994 ACM DBLP
151 A general lower bound on the number of examples needed for l.. (context) - Ehrenfeucht, Haussler et al. - 1989 ACM DBLP
146 Computers and Intractibility: A Guide to the Theory of NP-Co.. (context) - Garey, Johnson - 1979
144 Computational limitations on learning from examples (context) - Pitt, Valiant - 1988 ACM DBLP
142 Learning from noisy examples (context) - Angluin, Laird - 1988 ACM DBLP
139 Interpolation of scattered data: Distance matrices and condi.. (context) - Micchelli - 1986
123 the method of bounded differences (context) - McDiarmid - 1989
118 How to use expert advice (context) - Cesa-Bianchi, Freund et al. - 1993 ACM DBLP
115 the density of families of sets (context) - Sauer - 1972
102 Toward efficient agnostic learning - Kearns, Schapire et al. - 1992 ACM DBLP
92 Machine Learning: A Theoretical Approach (context) - Natarajan - 1991 DBLP
91 The sample complexity of pattern classification with neural .. - Bartlett - 1996
81 Equivalence of models for polynomial learnability (context) - Haussler, Kearns et al. - 1991 ACM DBLP
78 the learnability of Boolean formulae - Kearns, Li et al. - 1987
71 Scale-sensitive dimensions (context) - Alon, Ben-David et al. - 1993
66 Computational learning theory: survey and selected bibliogra.. (context) - Angluin - 1992 DBLP
66 Constant depth circuits (context) - Linial, Mansour et al. - 1989
64 Feedforward nets for interpolation and classification (context) - Sontag - 1992 ACM DBLP
59 Central limit theorems for empirical measures (context) - Dudley - 1978
59 Prediction preserving reducibility (context) - Pitt, Warmuth - 1990
52 The Computational Complexity of Machine Learning (context) - Kearns - 1989 ACM
45 The Design and Analysis of Efficient Learning Algorithms (context) - Schapire - 1991 ACM
44 Bounds on the computational power and learning complexity of.. - Maass - 1993
44 Fat-shattering and the learnability of real-valued functions - Bartlett, Long et al. - 1996 ACM DBLP
42 Learning simple concepts under simple distributions - Li, Vitanyi - 1991 ACM
37 Tracking drifting concepts by minimizing disagreements - Helmbold, Long - 1994 ACM DBLP
37 On learning sets and functions (context) - Natarajan - 1989 ACM DBLP
34 Learnability by fixed distributions (context) - Benedek, Itai - 1988 ACM DBLP
32 Neural Networks with Quadratic VC Dimension - Koiran, Sontag - 1997 ACM DBLP
31 Cryptographic hardness of distribution-specific learning (context) - Kharitonov - 1993 ACM DBLP
30 Robust trainability of single neurons - Hoffgen, Simon - 1992 ACM DBLP
26 Training a 3-node neural net is NP-Complete (context) - Blum, Rivest - 1989
25 the complexity of teaching - Goldman, Kearns - 1991
24 Bounding sample-size with the Vapnik-Chervonenkis dimension (context) - Shawe-Taylor, Anthony et al. - 1993
24 Polynomial bounds for VC Dimension of Sigmoidal Neural Netwo.. - Karpinski, Macintyre - 1995 ACM DBLP
24 Learnability with respect to fixed distributions (context) - Benedek, Itai - 1991 ACM DBLP
23 Neural nets with superlinear VC-dimension - Maass - 1994 ACM DBLP
21 Exact identification of circuits using fixed points of ampli.. (context) - Goldman, Kearns et al. - 1990
19 Tighter bounds of the VC-dimension of three-layer networks (context) - Sakurai - 1993
19 Teachability in computational learning (context) - Shinohara, Miyano - 1991 ACM DBLP
19 Improved learning of AC 0 functions - Furst, Jackson et al. - 1991
18 Learning DNF under the uniform distribution in quasi-polynom.. (context) - Verbeurgt - 1990 ACM DBLP
18 A learning criterion for stochastic rules (context) - Yamanishi - 1992 ACM DBLP
16 Characterizations of learnability for classes of f0; : : : ;.. (context) - Ben-David, Cesa-Bianchi et al. - 1995
16 The learnability of formal concepts (context) - Anthony, Biggs et al. - 1990 ACM DBLP
16 Tracking drifting concepts using random examples (context) - Helmbold, Long - 1991 ACM DBLP
16 Function learning from interpolation - Anthony, Bartlett - 1995 ACM DBLP
15 On specifying Boolean functions by labelled examples - Anthony, Brightwell et al. - 1995 ACM DBLP
15 Approximation and learning of convex superpositions (context) - Gurvits, Koiran ACM DBLP
14 Polynomial time algorithms for learning neural nets (context) - Baum - 1990 ACM DBLP
14 On exact specification by examples (context) - Anthony, Brightwell et al. - 1992 ACM DBLP
13 A combinatorial problem: Stability and order for models and .. (context) - Shelah - 1972
13 Bounds on the number of examples needed for learning functio.. - Simon - 1994 ACM DBLP
12 Learning in neural networks (context) - Judd - 1988 ACM DBLP
12 Sample sizes for multiple output threshold networks (context) - Shawe-Taylor, Anthony - 1991
11 the sample complexity of weak learning (context) - Goldman, Kearns et al. - 1990
11 Deductive learning (context) - Valiant - 1984 ACM
11 Learning with a slowly changing distribution - Bartlett - 1992 ACM DBLP
11 Learning nonoverlapping perceptron networks from examples an.. - Hancock, Golea et al. - 1994 ACM DBLP
10 Valid generalisation from approximate interpolation - Anthony, Bartlett et al. - 1996
9 the power of polynomial discriminators and radial basis func.. (context) - Anthony, Holden - 1993
9 Finiteness results for sigmoidal (context) - Macintyre, Sontag - 1993
9 Approximate testing and learnability (context) - Romanik - 1992 ACM DBLP
8 Probably approximate learning over classes of distributions (context) - Natarajan - 1992 ACM DBLP
7 the complexity of learning on feedforward neural nets (context) - Maass - 1993
7 Vapnik-Chervonenkis dimension bounds for two- and three-laye.. (context) - Bartlett - 1993
6 the complexity of function learning - Auer, Long et al. - 1993
6 Some weak learning results (context) - Helmbold, Warmuth - 1992 ACM DBLP
6 Dominating distributions and learnability (context) - Benedek, Itai - 1992 ACM DBLP
6 Polynomial uniform convergence and polynomial-sample learnab.. - Bertoni, Campadelli et al. - 1992 ACM
6 Occam's razor for functions (context) - Natarajan - 1993 ACM DBLP
5 Valid generalisation of functions from close approximations .. (context) - Anthony, Shawe-Taylor - 1994 ACM
5 Learning DNF formulae under classes of probability distribut.. (context) - Flammini, Marchetti-Spaccamela et al. - 1992 ACM DBLP
5 Computational learning theory for artificial neural networks - Anthony, Biggs - 1993
5 Structural risk minimisation over datadependent hierarchies (context) - Shawe-Taylor, Bartlett et al.
4 A sufficient condition for polynomial distribution-dependent.. - Anthony, Shawe-Taylor ACM DBLP
4 Lower bounds on the VC-dimension of smoothly parametrized fu.. - Lee, Bartlett et al. - 1995 ACM DBLP
3 Theory of Learning in Neural Networks (context) - Anthony, Bartlett
3 perceptron networks on the uniform distribution (context) - Golea, Marchand et al. - 1996
3 A greedy method for learning ¯-DNF functions under the unifo.. (context) - Pagallo, Haussler - 1989
2 The Vapnik-Chervonenkis dimension and pseudodimension of two.. (context) - Bartlett, Williamson - 1996
2 Testing as a dual to learning (context) - Romanik - 1991 ACM
2 Building symmetries into feedforward network architectures (context) - Shawe-Taylor - 1989
2 On learnability of monotone DNF functions under uniform dist.. (context) - Faigle, Kern - 1990
2 of London (London School of Economics and Political Science (context) - Anthony, Learnability et al. - 1991
2 A metric entropy bound is not sufficient for learnability - Dudley, Kulkarni et al. - 1994
2 Generalising from approximate interpolation (context) - Anthony, Shawe-Taylor - 1993
1 Strong unimodality and exact learning of constant depth ¯- p.. (context) - Marchand, Hadjifaradji - 1996
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.i.kyushu-u.ac.jp/~thomas/surveys.html):
The Complexity of Learning with Queries - Gavalda (1994) (Correct)
A Guided Tour Across the Boundaries of Learning Recursive.. - Zeugmann, Lange (1994) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC