Extracting Knowledge from Neural Networks

Extracting Knowledge from Neural Networks

Christie M. Fuller (Oklahoma State University, USA) and Rick L. Wilson (Oklahoma State University, USA)
Copyright: © 2006 |Pages: 9
DOI: 10.4018/978-1-59140-573-3.ch025
OnDemand PDF Download:
No Current Special Offers


Neural networks (NN) as classifier systems have shown great promise in many problem domains in empirical studies over the past two decades. Using case classification accuracy as the criteria, neural networks have typically outperformed traditional parametric techniques (e.g., discriminant analysis, logistic regression) as well as other non-parametric approaches (e.g., various inductive learning systems such as ID3, C4.5, CART, etc.).

Complete Chapter List

Search this Book: