Kernel methods for learning languages
TL;DR: In this paper, the authors study the linear separability of automata and languages by examining the rich class of piecewise-testable languages and prove that all languages linearly separable under a regular finite cover embedding are regular.
read more
About: This article is published in Theoretical Computer Science. The article was published on 01 Oct 2008. and is currently open access. The article focuses on the topics: Cone (formal languages) & Linear separability.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
On the index of Simon's congruence for piecewise testability
TL;DR: It is shown that, over a k-letter alphabet, the number of words modulo ~ n is in 2 ? ( n k - 1 log ? n ) .
64
•Dissertation
Kernel Methods for Nonlinear Identification, Equalization and Separation of Signals
Steven Van Vaerenbergh
- 03 Feb 2010
TL;DR: In this paper, the authors study the application of kernel methods in signal processing in this work, including the blind source separation, and the kernel recursive least-squares (KRLS) algorithm.
•Proceedings Article
String Extension Learning
Jeffrey Heinz
- 11 Jul 2010
TL;DR: The authors provides a unified, learning-theoretic analysis of several learnable classes of languages discussed previously in the literature, and provides a recipe for constructing new learnable models for aspects of natural language and cognition.
50
Learning languages with rational kernels
Corinna Cortes,Leonid Kontorovich,Mehryar Mohri +2 more
- 13 Jun 2007
TL;DR: A novel and general algorithm, double-tape disambiguation, that takes as input a transducer mapping sequences to sequence features, and yields an associated transducers that defines a finite range rational kernel is presented.
On the Complexity of k-Piecewise Testability and the Depth of Automata
Tomáš Masopust,Michaël Thomazo +1 more
- 27 Jul 2015
TL;DR: It is shown that the upper bound on k given by the depth of the minimal DFA can be exponentially bigger than the minimal possible k, and the complexity bound and detailed analysis for small k’s are provided.
References
Support-Vector Networks
Corinna Cortes,Vladimir Vapnik +1 more
TL;DR: High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Statistical learning theory
Vladimir Vapnik
- 01 Jan 1998
TL;DR: Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
30.4K
A training algorithm for optimal margin classifiers
Bernhard E. Boser,Isabelle Guyon,Vladimir Vapnik +2 more
- 01 Jul 1992
TL;DR: A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented, applicable to a wide variety of the classification functions, including Perceptrons, polynomials, and Radial Basis Functions.
Advances in kernel methods: support vector learning
Bernhard Schölkopf,Christopher John Burges,Alexander J. Smola +2 more
- 08 Feb 1999
TL;DR: Support vector machines for dynamic reconstruction of a chaotic system, Klaus-Robert Muller et al pairwise classification and support vector machines, Ulrich Kressel.
7.3K
Language identification in the limit
TL;DR: It was found that theclass of context-sensitive languages is learnable from an informant, but that not even the class of regular languages is learningable from a text.
3.8K