Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/3482
Title: | Learning strategy for the binary perceptron | Authors: | Reimers, L BOUTEN, Marcus VAN ROMPAEY, Bart |
Issue Date: | 1996 | Publisher: | IOP PUBLISHING LTD | Source: | JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 29(19). p. 6247-6252 | Abstract: | Pursuing the work of Penney and Sherrington, we determine the optimal continuous-weight perceptron which, on clipping, correctly predicts the largest number of weights for the binary perceptron with maximum stability. We calculate the fraction of correctly predicted binary weights when only the continuous weights stronger than a certain threshold are clipped. We finally carry out simulations for a perceptron with 50 weights to test the practicability of different learning strategies. | Notes: | Reimers, L, LIMBURGS UNIV CTR,UNIV CAMPUS,B-3590 DIEPENBEEK,BELGIUM. | Document URI: | http://hdl.handle.net/1942/3482 | DOI: | 10.1088/0305-4470/29/19/010 | ISI #: | A1996VL96000010 | Type: | Journal Contribution |
Appears in Collections: | Research publications |
Show full item record
SCOPUSTM
Citations
5
checked on Sep 2, 2020
WEB OF SCIENCETM
Citations
5
checked on Mar 29, 2024
Page view(s)
90
checked on Nov 7, 2023
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.