標題: Unsupervised query-based learning of neural networks using selective-attention and self-regulation
作者: Chang, RI
Hsiao, PY
交大名義發表
資訊工程學系
National Chiao Tung University
Department of Computer Science
關鍵字: force-directed method;query-based method;selective attention;self-organizing maps;self regulation;unsupervised learning
公開日期: 1-三月-1997
摘要: Query-based learning (QBL) has been introduced for training supervised network model with additional queried samples, Experiments demonstrated that the classification accuracy is further increased. Although QBL has been successfully applied to supervised neural networks, it is not suitable for unsupervised learning models without external supervisors. In this paper, an unsupervised QBL (UQBL) algorithm using selective-attention and self-regulation is proposed. Applying the selective-attention, we can ask the network to respond to its goal-directed behavior with self-focus. Since there is no supervisor to verify the self-focus, a compromise is then made to environment-focus with self-regulation. In this paper, we introduce UQBL1 and UQBL2 as two versions of UQBL; both of them can provide fast convergence. Our experiments indicate that the proposed methods are more insensitive to network initialization. They have better : generalization performance and can be a significant reduction in their training size.
URI: http://dx.doi.org/10.1109/72.557657
http://hdl.handle.net/11536/668
ISSN: 1045-9227
DOI: 10.1109/72.557657
期刊: IEEE TRANSACTIONS ON NEURAL NETWORKS
Volume: 8
Issue: 2
起始頁: 205
結束頁: 217
顯示於類別:期刊論文


文件中的檔案:

  1. A1997WM03800002.pdf