Bidirectional Activation-based Neural Network Learning Algorithm

Autor:	Igor Farkaš, Kristina Rebrova
Rok vydání:	2013
Předmět:	Error-driven learning Artificial neural network Computer science business.industry Neural network learning Artificial intelligence Sigmoid function business Algorithm Backpropagation
Zdroj:	Artificial Neural Networks and Machine Learning – ICANN 2013 ISBN: 9783642407277 ICANN
DOI:	10.1007/978-3-642-40728-4_20
Popis:	We present a model of a bidirectional three-layer neural network with sigmoidal units, which can be trained to learn arbitrary mappings. We introduce a bidirectional activation-based learning algorithm (BAL), inspired by O'Reilly's supervised Generalized Recirculation (GeneRec) algorithm that has been designed as a biologically plausible alternative to standard error backpropagation. BAL shares several features with GeneRec, but differs from it by being completely bidirectional regarding the activation propagation and the weight updates. In pilot experiments, we test the learning properties of BAL using three artificial data sets with binary patterns of increasing complexity.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::16f241197e3d3a58a0f00045aee170bd https://doi.org/10.1007/978-3-642-40728-4_20 Zobrazit plný text záznamu