查詢結果分析
來源資料
頁籤選單縮合
題名 | A Hebbian-Based Neural Network for Principal Components Analysis=以Hebbian-Based類神經網路解決主成分分析問題 |
---|---|
作者 | 戴文彬; Tai, Wen-pin; |
期刊 | 華岡工程學報 |
出版日期 | 20020600 |
卷期 | 16 2002.06[民91.06] |
頁次 | 頁97-109 |
分類號 | 312.2 |
語文 | eng |
關鍵詞 | 類神經網路; 主成分分析; 神經元自知調節; Neural networks; Principal components analysis; Self-regulation; |
中文摘要 | 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子空間分解中的主成分分析問題,及其相關應用。 |
英文摘要 | 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 thought 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. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。