Diverse Evolutionary Neural Networks Based on Information Theory

There is no consensus on measuring distances between two different neural network architectures. Two folds of methods are used for that purpose: Structural and behavioral distance measures. In this paper, we focus on the later one that compares differences based on output responses given the same input. Usually neural network output can be interpreted as a probabilistic function

• Type: Conference
• Year: 2007
• Where: ICONIP
• Authors: Kyung-Joong Kim, Sung-Bae Cho
• Keywords: ICONIP 2007, Information Technology, Neural Network, Neural Network Architectures, Neural Network Output