Design of Multilayer Perceptrons for Pattern Classifications
패턴인식 문제에 대한 다층퍼셉트론의 설계 방법

Sang-Hoon Oh
2010 The Journal of the Korea Contents Association  
Multilayer perceptrons(MLPs) or feed-forward neural networks are widely applied to many areas based on their function approximation capabilities. When implementing MLPs for application problems, we should determine various parameters and training methods. In this paper, we discuss the design of MLPs especially for pattern classification problems. This discussion includes how to decide the number of nodes in each layer, how to initialize the weights of MLPs, how to train MLPs among various error
more » ... functions, the imbalanced data problems, and deep architecture. ■ keyword :|Multilayer Perceptron|Pattern Classification|Design Rule|Node Number|Error Function| * 본 논문은 한국콘텐츠학회 ICCC2009 국제학술대회 우수논문입니다.
doi:10.5392/jkca.2010.10.5.099 fatcat:qqny67qstzhvfaxj5r6fqzesoi