Evolutionary Training Data Sets with N{dimensional Encoding for Neural Insar Classiiers

Abstract

Supervised training of a neural classi-er and its performance not only relies on the arti-cial neural network (ANN) type, architecture and the training method, but also on the size and composition of the training data set (TDS). For the parallel generation of TDSs for a multi{layer perceptron (MLP) classiier we introduce evolutionary resam-pling and combine… (More)

2 Figures and Tables

Topics

  • Presentations referencing similar topics