A SimpleHierarchicalApproximation RBF Neural
Peggy Israel Doerschuk, Sainath Shrikant Pawaskar · 2005
Theapproximation algorithm introduced by AsimRoyetal.(lJ generates a hybrid neural network withRBFneurons andothertypes ofhidden neuronsfor function approximation. Thenetwork istrained instages, withRBF neurons attheearly stages corresponding to general features inthespaceandthoseinlater stages corresponding tomorespecific features. Theothertypes ofhidden neurons areaddedwitha viewtoimproving generalization andreducing thenumberofRBF neurons. Thealgorithm useslinear programming todesign and train thehybrid network. We investigate simplifying the algorithm withaviewtoeliminating theneedfortheother types ofhidden neurons andlinear programming. The Simple Hierarchical Approximation algorithm ('SHA') achieves comparable results intermsofaccuracy without theaddedcomplexity introduced bytheothertypesof hidden neurons.