Publication | Closed Access
Output weight optimization for the multi-layer perceptron
19
Citations
6
References
2003
Year
Unknown Venue
Search OptimizationEngineeringMachine LearningNeural Networks (Machine Learning)Multi-layer PerceptronMultilayer PerceptronSocial SciencesPattern RecognitionSparse Neural NetworkPolynomial Basis FunctionsMachine Learning ModelComputer EngineeringComputer ScienceNeural Networks (Computational Neuroscience)Neural NetworksNeural Architecture SearchSignal ProcessingModel OptimizationDeep Neural NetworksEvolving Neural NetworkBrain-like Computing
A fast method for designing multilayer perceptron (MLP) neural networks was introduced by S.A. Barton (1991). In this method, linear equations are solved for the output weights. An analysis of the MLP based on polynomial basis functions (PBFs) is used to justify the technique. A conjugate gradient solution to the output weight equations is introduced. A mutation technique that can be used to improve hidden unit weights is described. The output weight optimization (OWO) technique is extended to classification networks, which have nonlinear output unit activations. In several examples, it is seen that OWO is significantly faster than backpropagation (BP).< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
| Year | Citations | |
|---|---|---|
Page 1
Page 1