You are in : Home » Results & submissions » Select UOA » 11 - Computer Science and Informatics » View submission: Royal Holloway, University of London » Outputs » Detail

Output details

11 - Computer Science and Informatics

Royal Holloway, University of London

Return to search Previous output Next output

Output 51 of 90 in the submission

Article title

Languages as hyperplanes: grammatical inference with string kernels

Type

D - Journal article

DOI

10.1007/s10994-010-5218-3

Title of journal

Machine Learning

Article number

Volume number

Issue number

First page of article

351

ISSN of journal

0885-6125

Year of publication

2011

URL

http://link.springer.com/article/10.1007%2Fs10994-010-5218-3

Number of additional authors

Additional information

<10>This paper reports a new method for defining formal languages: words are implicitly mapped to points in a high-dimensional feature space, using a positive-definite SVM kernel function; a language is then defined as those words that lie on a hyperplane in the feature space. All such languages are therefore learnable and recognisable using linear algebra. This paper extends our previous work by providing extended language classes and proofs of learnability. This is one of the very few formal learnability results for language classes that include some context-sensitive languages. These languages cross-cut the Chomsky hierarchy.

Interdisciplinary

Cross-referral requested

Research group

B - Computer Learning Research Centre

Citation count

Proposed double-weighted

Double-weighted statement

Reserve for a double-weighted output

Non-English

English abstract