A Hebbian-Based Neural Network for Principal Components Analysis

CCUR > College of Natural Science and Engineering > College of Engineering > College of Engineering > Chinese Culture University Hwa Kang Journal of Engineering > Item 987654321/22227

Please use this identifier to cite or link to this item: https://irlib.pccu.edu.tw/handle/987654321/22227

Title:	A Hebbian-Based Neural Network for Principal Components Analysis
Authors:	戴文彬
Contributors:	工學院
Keywords:	類神經網路主成分分析神經元自知調節 Neural Networks Principal Components Analysis Self-Regulation
Date:	2002-06-01
Issue Date:	2012-05-09 15:08:10 (UTC+8)
Abstract:	本論文中，我們提出一個新的Hebbian-based類神經網路學習模型，並將其應用於解決資料特徵分析時的主成分分析問題。這個類神經網路的基本觀念，是利用神經元自知調節的運作方式，達到整體學習的結果。依此觀念，我們推導出新的學習演算法則，並進一步有效地解決了空間分解中的主成分分析問題，及其相關應用。 In this paper, we propose a new learning paradigm of neural network and apply it to solve the subspace decomposition problem for principal components analysis. In this proposed network, each neuron learns about the environment through a process of Hebbian-based self-regulation which actively controls the neuron's own learning by perceiving its status in overall learning effectiveness. Based on this concept of self-regulation, we derive the primary learning rules of the synaptic adaptation in the network. The Hebbian-based self-regulative neural network is utilized to explore significant features of the environment data in an unsupervised way and to implement subspace decomposition of the data space. Numerical simulations demonstrate the efficiency of the learning model and verify the practicability of the concept of individual neuronal self-regulation for learning control.
Relation:	華岡工程學報 16期 p.97 -109
Appears in Collections:	[College of Engineering] Chinese Culture University Hwa Kang Journal of Engineering

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	467	View/Open

Loading...