Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Institution
- Publication
- Publication Type
Articles 1 - 2 of 2
Full-Text Articles in Physical Sciences and Mathematics
The Inefficiency Of Batch Training For Large Training Sets, Tony R. Martinez, D. Randall Wilson
The Inefficiency Of Batch Training For Large Training Sets, Tony R. Martinez, D. Randall Wilson
Faculty Publications
Multilayer perceptrons are often trained using error backpropagation (BP). BP training can be done in either a batch or continuous manner. Claims have frequently been made that batch training is faster and/or more "correct" than continuous training because it uses a better approximation of the true gradient for its weight updates. These claims are often supported by empirical evidence on very small data sets. These claims are untrue, however, for large training sets. This paper explains why batch training is much slower than continuous training for large training sets. Various levels of semi-batch training used on a 20,000-instance speech recognition …
Control Chart Pattern Recognition Using Artificial Neural Networks, Şeref Sağiroğlu, Erkan Beşdok, Mehmet Erler
Control Chart Pattern Recognition Using Artificial Neural Networks, Şeref Sağiroğlu, Erkan Beşdok, Mehmet Erler
Turkish Journal of Electrical Engineering and Computer Sciences
Precise and fast control chart pattern (CCP) recognition is important for monitoring process environments to achieve appropriate control and to produce high quality products. CCPs can exhibit six types of pattern: normal, cyclic, increasing trend, decreasing trend, upward shift and downward shift. Except for normal patterns, all other patterns indicate that the process being monitored is not functioning correctly and requires adjustment. This paper describes a new type of neural network for speeding up the training process and to compare three training algorithms in terms of speed, performance and parameter complexity for CCP recognition. The networks are multilayered perceptrons trained …