dc.contributor.author | Albrecht, A. | |
dc.contributor.author | Wong, C.K. | |
dc.date.accessioned | 2011-02-21T09:18:05Z | |
dc.date.available | 2011-02-21T09:18:05Z | |
dc.date.issued | 2001 | |
dc.identifier.citation | Albrecht , A & Wong , C K 2001 , ' Combining the perception algorithm with logarithmic simulated annealing ' , Neural Processing Letters , vol. 14 , no. 1 , pp. 75-83 . https://doi.org/10.1023/A:1011369322571 | |
dc.identifier.issn | 1370-4621 | |
dc.identifier.other | dspace: 2299/5348 | |
dc.identifier.uri | http://hdl.handle.net/2299/5348 | |
dc.description | The original publication is available at www.springerlink.com Copyright Springer [Full text of this article is not available in the UHRA] | |
dc.description.abstract | We present results of computational experiments with an extension of the Perceptron algorithm by a special type of simulated annealing. The simulated annealing procedure employs a logarithmic cooling schedule (-), where (-) is a parameter that depends on the underlying configuration space. For sample sets S of n-dimensional vectors generated by randomly chosen polynomials (-), we try to approximate the positive and negative examples by linear threshold functions. The approximations are computed by both the classical Perceptron algorithm and our extension with logarithmic cooling schedules. For (-) and (-), the extension outperforms the classical Perceptron algorithm by about 15% when the sample size is sufficiently large. The parameter was chosen according to estimations of the maximum escape depth from local minima of the associated energy landscape. | en |
dc.language.iso | eng | |
dc.relation.ispartof | Neural Processing Letters | |
dc.subject | cooling schedules | |
dc.subject | neural networks | |
dc.subject | perceptron algorithm | |
dc.subject | simulated annealing | |
dc.subject | threshold functions | |
dc.title | Combining the perception algorithm with logarithmic simulated annealing | en |
dc.contributor.institution | School of Computer Science | |
dc.contributor.institution | Science & Technology Research Institute | |
dc.description.status | Peer reviewed | |
rioxxterms.versionofrecord | 10.1023/A:1011369322571 | |
rioxxterms.type | Journal Article/Review | |
herts.preservation.rarelyaccessed | true | |