翻訳と辞書 Words near each other ・ Generation Adidas ・ Generation Adidas Cup ・ Generation Bass ・ Generation Catalano ・ Generation Cross ・ Generation Cryo ・ Generation Dead ・ Generation effect ・ Generation EFX ・ Generalized game theory ・ Generalized gamma distribution ・ Generalized Gauss–Bonnet theorem ・ Generalized Gauss–Newton method ・ Generalized geography ・ Generalized granuloma annulare ・ Generalized Hebbian Algorithm ・ Generalized helicoid ・ Generalized Helmholtz theorem ・ Generalized hypergeometric function ・ Generalized hyperhidrosis ・ Generalized integer gamma distribution ・ Generalized inverse ・ Generalized inverse Gaussian distribution ・ Generalized inversive congruential pseudorandom numbers ・ Generalized iterative scaling ・ Generalized Jacobian ・ Generalized Kac–Moody algebra ・ Generalized keyboard ・ Generalized Korteweg–de Vries equation ・ Generalized Lagrangian mean Dictionary Lists mini英和辞書 mini和英辞書 Webster 1913 Latin-English FOLDOC Wikipedia English ウィキペディア

翻訳と辞書　辞書検索 [ 開発暫定版 ] スポンサード リンク Generalized Hebbian Algorithm ： ウィキペディア英語版 Generalized Hebbian Algorithm The Generalized Hebbian Algorithm (GHA), also known in the literature as Sanger's rule, is a linear feedforward neural network model for unsupervised learning with applications primarily in principal components analysis. First defined in 1989, it is similar to Oja's rule in its formulation and stability, except it can be applied to networks with multiple outputs. The name originates because of the similarity between the algorithm and a hypothesis made by Donald Hebb about the way in which synaptic strengths in the brain are modified in response to experience, i.e., that changes are proportional to the correlation between the firing of pre- and post-synaptic neurons. ==Theory== GHA combines Oja's rule with the Gram-Schmidt process to produce a learning rule of the form :$\backslash ,\backslash Delta\; w\_\; ~\; =\; ~\; \backslash eta\backslash left(y\_i\; x\_j\; -\; y\_i\; \backslash sum\_^\; w\_\; y\_k\; \backslash right)$, where defines the synaptic weight or connection strength between the th input and th output neurons, and are the input and output vectors, respectively, and is the ''learning rate'' parameter. 抄文引用元・出典: フリー百科事典『 ウィキペディア（Wikipedia）』 ■ウィキペディアで「Generalized Hebbian Algorithm」の詳細全文を読む スポンサード リンク 翻訳と辞書 : 翻訳のためのインターネットリソース Copyright(C) kotoba.ne.jp 1997-2016. All Rights Reserved.