Keyword

concept classes

Description: In computational learning theory, concept classes are sets of possible concepts, commonly represented as collections of labeled instances to be learned from data.

Primary topic: Machine Learning and Algorithms (52%)

Wikidata ID: wiki/Q5158394

OpenAlex ID: keywords/concept-classes

The strength of weak learnability

1990 · Robert E. Schapire · Machine Learning · 2,451

PDF

Learning from Observation: Conceptual Clustering

1983 · Ryszard S. Michalski, Robert E. Stepp · Machine Learning · 537

Some PAC-Bayesian theorems

1998 · David A. McAllester · 467

A general lower bound on the number of examples needed for learning

1989 · Andrzej Ehrenfeucht, David Haussler, et al. · Information and Computation · 411

A review of multi-instance learning assumptions

2010 · James Foulds, Eibe Frank · The Knowledge Engineering Review · 388

What Can We Learn Privately?

2008 · Shiva Prasad Kasiviswanathan, Homin K. Lee, et al. · Annual Symposium on Foundations of Computer Science · 334

PDF

An algorithmic theory of learning: Robust concepts and random projection

2006 · Rosa I. Arriaga, Santosh Vempala · Machine Learning · 316

PDF

Sample Compression, Learnability, and the Vapnik-Chervonenkis Dimension

1995 · Sally Floyd, Manfred Warmuth · Machine Learning · 257

PDF

On the Complexity of Teaching

1995 · S.A. Goldman, M.J. Kearns · Journal of Computer and System Sciences · 257

The strength of weak learnability

1989 · R.E. Schapire · Annual Symposium on Foundations of Computer Science · 257

Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers

2018 · Allen-Zhu, Zeyuan, Li, Yuanzhi, et al. · arXiv (Cornell University) · 243

PDF

A linear lower bound on the unbounded error probabilistic communication complexity

2002 · Jürgen Forster · Journal of Computer and System Sciences · 181

PDF

Classifying learnable geometric concepts with the Vapnik-Chervonenkis dimension

1986 · A Blumer, A Ehrenfeucht, et al. · 161

The Strength of Weak Learnability

1989 · Robert E. Schapire · Elsevier eBooks · 147

Equivalence of models for polynomial learnability

1991 · David Haussler, Michael Kearns, et al. · Information and Computation · 138

Learning functions represented as multiplicity automata

2000 · Amos Beimel, Francesco Bergadano, et al. · Journal of the ACM · 121

PDF

Efficient NC algorithms for set cover with applications to learning and geometry

1994 · Bonnie Berger, John Rompel, et al. · Journal of Computer and System Sciences · 119

Recent Results on Boolean Concept Learning

1987 · MICHAEL KEARNS, MING LI, et al. · Elsevier eBooks · 119

Learnability with respect to fixed distributions

1991 · Gyora M. Benedek, Alon Itai · Theoretical Computer Science · 109

Generalized teaching dimensions and the query complexity of learning

1995 · Tibor Hegedűs · Annual Conference on Computational Learning Theory (COLT) · 101

PDF

How many queries are needed to learn?

1996 · Lisa Hellerstein, Krishnan Pillaipakkamnatt, et al. · Journal of the ACM · 94

PDF

Bounds on the Sample Complexity for Private Learning and Private Data Release

2010 · Amos Beimel, Shiva Prasad Kasiviswanathan, et al. · Lecture notes in computer science · 91

PAC learning axis-aligned rectangles with respect to product distributions from multiple-instance examples

1996 · Philip M. Long, Lei Tan · Annual Conference on Computational Learning Theory (COLT) · 88

Limitations of Learning via Embeddings in Euclidean Half-Spaces

2001 · Shai Ben-David, Nadav Eiron, et al. · Lecture notes in computer science · 86

On learning a union of half spaces

1990 · Eric B Baum · Journal of Complexity · 78

Works count: 588

Citation count: 11,860