Neural Network Training Using Multi - channel Data withAggregate

Abstract

The solution of classiication problems using statistical techniques requires appropriately labelled training data. In the case of multi-channel data, however, the labels may only be available in aggregate form rather than as separate labels for each individual channel. Standard techniques, using a trained model to predict each channel separately, are… (More)

Topics

Cite this paper

@inproceedings{McGrogan1999NeuralNT, title={Neural Network Training Using Multi - channel Data withAggregate}, author={LabellingN McGrogan and C M Bishopy}, year={1999} }