2005 Special issue: Training neural networks with heterogeneous data

Authors:
John A. Drakopoulos;Ahmad Abdulkader
Affiliations:
Tablet PC Handwriting Recognition Group, Microsoft Corporation, One Microsoft Way, Redmond, WA 98052-6399, USA;Tablet PC Handwriting Recognition Group, Microsoft Corporation, One Microsoft Way, Redmond, WA 98052-6399, USA
Venue:
Neural Networks - 2005 Special issue: IJCNN 2005
Year:
2005

Citing 2
Cited 0

Growing cell structures—a self-organizing network for unsupervised and supervised learning

Neural Networks
Adaptive mixtures of local experts

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Data pruning and ordered training are two methods and the results of a small theory that attempts to formalize neural network training with heterogeneous data. Data pruning is a simple process that attempts to remove noisy data. Ordered training is a more complex method that partitions the data into a number of categories and assigns training times to those assuming that data size and training time have a polynomial relation. Both methods derive from a set of premises that form the 'axiomatic' basis of our theory. Both methods have been applied to a time-delay neural network-which is one of the main learners in Microsoft's Tablet PC handwriting recognition system. Their effect is presented in this paper along with a rough estimate of their effect on the overall multi-learner system. The handwriting data and the chosen language are Italian.