Extraction of Feature Attentive Regions in a Learnt Neural Network (Special Issue on Neurocomputing)

スポンサーリンク

概要

• 論文の詳細を見る

• This paper proposed a new method of extracting feature attentive regions in a learnt multi-layer neural network. We define a function which calculates the degree of dependence of an output unit on an input unit. The value of this function can be used to investigate whether a learnt network detects the feature regions in the training patterns. Three computer simulations are presented: (1) investigation of the basic characteristic of this function; (2) application of our method to a simple pattern classification task; (3) application of our method to a large scale pattern classification task.

• 社団法人電子情報通信学会の論文
• 1994-04-25

著者

• IWAHORI Yuji

  Faculty of Engineering, Chubu University

• Ishii Naohiro

  Faculty of Engineering, Nagoya Institute of Technology

• Iwahori Yuji

  Faculty Of Engineering Nagoya Institute Of Technology

• Ishii Naohiro

  Faculty Of Engineering Nagoya Institute Of Technology

• Sano Hideki

  Faculty of Engineering, Nagoya Institute of Technology

• Nada Atsuhiro

  Faculty of Engineering, Nagoya Institute of Technology

• Sano Hideki

  Faculty Of Engineering Nagoya Institute Of Technology

• Nada Atsuhiro

  Faculty Of Engineering Nagoya Institute Of Technology

関連論文

• Extraction of Moving Objects by Estimating Background Brightness
• Moving Point Light Source Photometric Stereo
• Photometric Stereo for Specular Surface Shape Based on Neural Network (Special Issue on Neurocomputing)
• Classification of Surface Curvature from Shading Images Using Neural Network
• Extraction of Feature Attentive Regions in a Learnt Neural Network (Special Issue on Neurocomputing)
• Detection of the K-Complex Using a New Method of Recognizing Waveform Based on the Discrete Wavelet Transform
• The Recognition System with Two Channels at Different Resolution for Detecting Spike in Human's EEG

スポンサーリンク