A Forward-propagaton Learning Rule Acquires Neural Inverse Models by Maximum Likelihood Estimation

Autor:	Yoshihiro Ohama, Naohiro Fukumura, Yoji Uno
Rok vydání:	2006
Předmět:	Current (mathematics) Computer science business.industry Maximum likelihood Work (physics) Linear regression Learning rule Inverse Pattern recognition Artificial intelligence Covariance Motor learning business
Zdroj:	The Brain & Neural Networks. 13:101-110
ISSN:	1883-0455 1340-766X
DOI:	10.3902/jnns.13.101
Popis:	A forward-propagation learning rule (FPL) has been proposed for acquiring neural inverse models without back-propagated signals based on a Newton-like method. A modified multiple linear regression, RLS algorithms or a Fisher's scoring method have been applied to the FPL, although these methods does not necessarily achieve goal-directed learning. In the current work, to guarantee goal-directed learning, a modified method for FPL is derived as one of gradient methods in terms of maximum likelihood estimation. The forward-propagated errors on the learning model and the covariance matrices are evaluated to calculate the gradients which are used in the proposed method. The suitability of the proposed method is confirmed by computer simulation in motor learning.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::cab9fccc89395f16c5b6a1b68e688d6e https://doi.org/10.3902/jnns.13.101 Zobrazit plný text záznamu