Journal ArticleDOI
Learnability and the Vapnik-Chervonenkis dimension
Reads0
Chats0
TLDR
This paper shows that the essential condition for distribution-free learnability is finiteness of the Vapnik-Chervonenkis dimension, a simple combinatorial parameter of the class of concepts to be learned.Abstract:
Valiant's learnability model is extended to learning classes of concepts defined by regions in Euclidean space En. The methods in this paper lead to a unified treatment of some of Valiant's results, along with previous results on distribution-free convergence of certain pattern recognition algorithms. It is shown that the essential condition for distribution-free learnability is finiteness of the Vapnik-Chervonenkis dimension, a simple combinatorial parameter of the class of concepts to be learned. Using this parameter, the complexity and closure properties of learnable classes are analyzed, and the necessary and sufficient conditions are provided for feasible learnability.read more
Citations
More filters
Posted Content
DNF-Net: A Neural Architecture for Tabular Data
TL;DR: This work presents DNF-Net a novel generic architecture whose inductive bias elicits models whose structure corresponds to logical Boolean formulas in disjunctive normal form (DNF) over affine soft-threshold decision terms, which opens the door to practical end-to-end handling of tabular data using neural networks.
Journal ArticleDOI
Sharpening Occam's razor
TL;DR: A new representation-independent formulation of Occam's razor theorem, based on Kolmogorov complexity, is provided, which allows for a sharper reverse than that of Board and Pitt and extends the reverse to superpolynomial running times.
Journal ArticleDOI
Embracing the disharmony in medical imaging: A Simple and effective framework for domain adaptation
TL;DR: In this paper , a simple but effective framework for tackling domain shift is proposed, based on the theoretical arguments, to build a pretrained classifier on the source data and adapt this model to new data, which can be fine-tuned for intra-study domain adaptation.
Book ChapterDOI
Typed Meta−interpretive Learning of Logic Programs
TL;DR: This work claims that adding types to MIL can improve learning performance and shows that types can substantially reduce learning times, and introduces two typed MIL systems: Metagol and HEXMIL.
Journal ArticleDOI
Rock’n’roll PUFs: crafting provably secure pufs from less secure ones (extended version)
TL;DR: This paper provides an example of somewhat hard PUFs and demonstrates how to build a strongly secure construction out of these considerably weaker primitives.
References
More filters
Book
Computers and Intractability: A Guide to the Theory of NP-Completeness
TL;DR: The second edition of a quarterly column as discussed by the authors provides a continuing update to the list of problems (NP-complete and harder) presented by M. R. Garey and myself in our book "Computers and Intractability: A Guide to the Theory of NP-Completeness,” W. H. Freeman & Co., San Francisco, 1979.
Book
The Art of Computer Programming
TL;DR: The arrangement of this invention provides a strong vibration free hold-down mechanism while avoiding a large pressure drop to the flow of coolant fluid.
Journal ArticleDOI
Pattern Classification and Scene Analysis.
Book
Pattern classification and scene analysis
Richard O. Duda,Peter E. Hart +1 more
TL;DR: In this article, a unified, comprehensive and up-to-date treatment of both statistical and descriptive methods for pattern recognition is provided, including Bayesian decision theory, supervised and unsupervised learning, nonparametric techniques, discriminant analysis, clustering, preprosessing of pictorial data, spatial filtering, shape description techniques, perspective transformations, projective invariants, linguistic procedures, and artificial intelligence techniques for scene analysis.