Matches in SemOpenAlex for { <https://semopenalex.org/work/W2000703390> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W2000703390 abstract "Many techniques have been developed in recent years in order to speed up the training process of Multilayer Perceptrons (MLPs), such as accelerated versions of gradient descent, second order methods, Kalman related algorithms, and block learning methods; among them, the latter offer a reasonable way of reducing training effort and getting good results with MLPs. However, they usually find suboptimal solutions and, sometimes, the values obtained for the weights are excessively large. In this paper, we analyze the drawbacks of these block methods using a very simple test model, we propose several modifications by discarding samples (DS- LSB), using controlled perturbation (CP-LSB), and by means of a Reduced Sensitivity version (RS-LSB) and we also extend their forms to include some especial characteristics: we propose a robust training algorithm relying on Total Least Squares (TLS) minimizations (the so-called RS-TLS algorithm), useful for noisy training patterns, and we also present a method for training MLPs with general output cost function (the `RS-WLSB' algorithm). The advantages of these methods with respect to related algorithms are illustrated using several test problems. Finally, we extract some conclusions and propose, as a further work, the development of recursive implementations, able to learn on-line and to deal with non-stationary problems, and the application of block training methods to recurrent networks.© (1997) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only." @default.
- W2000703390 created "2016-06-24" @default.
- W2000703390 creator A5054700423 @default.
- W2000703390 creator A5064315752 @default.
- W2000703390 date "1997-04-04" @default.
- W2000703390 modified "2023-09-23" @default.
- W2000703390 title "<title>Block training methods for perceptrons and their applications</title>" @default.
- W2000703390 doi "https://doi.org/10.1117/12.271522" @default.
- W2000703390 hasPublicationYear "1997" @default.
- W2000703390 type Work @default.
- W2000703390 sameAs 2000703390 @default.
- W2000703390 citedByCount "0" @default.
- W2000703390 crossrefType "proceedings-article" @default.
- W2000703390 hasAuthorship W2000703390A5054700423 @default.
- W2000703390 hasAuthorship W2000703390A5064315752 @default.
- W2000703390 hasConcept C11413529 @default.
- W2000703390 hasConcept C119857082 @default.
- W2000703390 hasConcept C153258448 @default.
- W2000703390 hasConcept C154945302 @default.
- W2000703390 hasConcept C2524010 @default.
- W2000703390 hasConcept C2777210771 @default.
- W2000703390 hasConcept C33923547 @default.
- W2000703390 hasConcept C41008148 @default.
- W2000703390 hasConcept C50644808 @default.
- W2000703390 hasConcept C60908668 @default.
- W2000703390 hasConceptScore W2000703390C11413529 @default.
- W2000703390 hasConceptScore W2000703390C119857082 @default.
- W2000703390 hasConceptScore W2000703390C153258448 @default.
- W2000703390 hasConceptScore W2000703390C154945302 @default.
- W2000703390 hasConceptScore W2000703390C2524010 @default.
- W2000703390 hasConceptScore W2000703390C2777210771 @default.
- W2000703390 hasConceptScore W2000703390C33923547 @default.
- W2000703390 hasConceptScore W2000703390C41008148 @default.
- W2000703390 hasConceptScore W2000703390C50644808 @default.
- W2000703390 hasConceptScore W2000703390C60908668 @default.
- W2000703390 hasLocation W20007033901 @default.
- W2000703390 hasOpenAccess W2000703390 @default.
- W2000703390 hasPrimaryLocation W20007033901 @default.
- W2000703390 hasRelatedWork W1505888673 @default.
- W2000703390 hasRelatedWork W1567451679 @default.
- W2000703390 hasRelatedWork W1567571245 @default.
- W2000703390 hasRelatedWork W1570412446 @default.
- W2000703390 hasRelatedWork W1642806187 @default.
- W2000703390 hasRelatedWork W2032381427 @default.
- W2000703390 hasRelatedWork W2071050550 @default.
- W2000703390 hasRelatedWork W2084362125 @default.
- W2000703390 hasRelatedWork W2085159862 @default.
- W2000703390 hasRelatedWork W2110158084 @default.
- W2000703390 hasRelatedWork W2114367267 @default.
- W2000703390 hasRelatedWork W2126291888 @default.
- W2000703390 hasRelatedWork W2135272206 @default.
- W2000703390 hasRelatedWork W2150139843 @default.
- W2000703390 hasRelatedWork W2150634210 @default.
- W2000703390 hasRelatedWork W2153232138 @default.
- W2000703390 hasRelatedWork W2171392412 @default.
- W2000703390 hasRelatedWork W2725952151 @default.
- W2000703390 hasRelatedWork W2771575470 @default.
- W2000703390 hasRelatedWork W2615909838 @default.
- W2000703390 isParatext "false" @default.
- W2000703390 isRetracted "false" @default.
- W2000703390 magId "2000703390" @default.
- W2000703390 workType "article" @default.