4 April 1997 MLP iterative construction algorithm
Author Affiliations +
Abstract
The MLP Iterative Construction Algorithm (MICA) designs a Multi-Layer Perceptron (MLP) neural network as it trains. MICA adds Hidden Layer Nodes one at a time, separating classes on a pair-wise basis, until the data is projected into a linear separable space by class. Then MICA trains the Output Layer Nodes, which results in an MLP that achieves 100% accuracy on the training data. MICA, like Backprop, produces an MLP that is a minimum mean squared error approximation of the Bayes optimal discriminant function. Moreover, MICA's training technique yields novel feature selection technique and hidden node pruning technique
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Thomas F. Rathbun, Steven K. Rogers, Martin P. DeSimio, Mark E. Oxley, "MLP iterative construction algorithm", Proc. SPIE 3077, Applications and Science of Artificial Neural Networks III, (4 April 1997); doi: 10.1117/12.271467; https://doi.org/10.1117/12.271467
PROCEEDINGS
9 PAGES


SHARE
Back to Top