Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Computer Sciences
A Noise Filtering Method Using Neural Networks, Tony R. Martinez, Xinchuan Zeng
A Noise Filtering Method Using Neural Networks, Tony R. Martinez, Xinchuan Zeng
Faculty Publications
During the data collecting and labeling process it is possible for noise to be introduced into a data set. As a result, the quality of the data set degrades and experiments and inferences derived from the data set become less reliable. In this paper we present an algorithm, called ANR (automatic noise reduction), as a filtering mechanism to identify and remove noisy data items whose classes have been mislabeled. The underlying mechanism behind ANR is based on a framework of multi-layer artificial neural networks. ANR assigns each data item a soft class label in the form of a class probability …
Speed Training: Improving The Rate Of Backpropagation Learning Through Stochastic Sample Presentation, Timothy L. Andersen, Tony R. Martinez, Michael E. Rimer
Speed Training: Improving The Rate Of Backpropagation Learning Through Stochastic Sample Presentation, Timothy L. Andersen, Tony R. Martinez, Michael E. Rimer
Faculty Publications
Artificial neural networks provide an effective empirical predictive model for pattern classification. However, using complex neural networks to learn very large training sets is often problematic, imposing prohibitive time constraints on the training process. We present four practical methods for dramatically decreasing training time through dynamic stochastic sample presentation, a technique we call speed training. These methods are shown to be robust to retaining generalization accuracy over a diverse collection of real world data sets. In particular, the SET technique achieves a training speedup of 4278% on a large OCR database with no detectable loss in generalization.
A Multi-Chip Module Implementation Of A Neural Network, Tony R. Martinez, George L. Rudolph, Linton G. Salmon, Matthew G. Stout
A Multi-Chip Module Implementation Of A Neural Network, Tony R. Martinez, George L. Rudolph, Linton G. Salmon, Matthew G. Stout
Faculty Publications
The requirement for dense interconnect in artificial neural network systems has led researchers to seek high-density interconnect technologies. This paper reports an implementation using multi-chip modules (MCMs) as the interconnect medium. The specific system described is a self-organizing, parallel, and dynamic learning model which requires a dense interconnect technology for effective implementation; this requirement is fulfilled by exploiting MCM technology. The ideas presented in this paper regarding an MCM implementation of artificial neural networks are versatile and can be adapted to apply to other neural network and connectionist models.