A training algorithm for binary feedforward neural networks
- 1 March 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 3 (2) , 176-194
- https://doi.org/10.1109/72.125859
Abstract
The authors present a new training algorithm to be used on a four-layer perceptron-type feedforward neural network for the generation of binary-to-binary mappings. This algorithm is called the Boolean-like training algorithm (BLTA) and is derived from original principles of Boolean algebra followed by selected extensions. The algorithm can be implemented on analog hardware, using a four-layer binary feedforward neural network (BFNN). The BLTA does not constitute a traditional circuit building technique. Indeed, the rules which govern the BLTA allow for generalization of data in the face of incompletely specified Boolean functions. When compared with techniques which employ descent methods, training times are greatly reduced in the case of the BLTA. Also, when the BFNN is used in conjunction with A/D converters, the applicability of the present algorithm can be extended to accept real-valued inputs.<>Keywords
This publication has 5 references indexed in Scilit:
- The Training and Use of an Artificial Neural Network to Monitor Use of Medication in Treatment of Complex Patients*Journal of Clinical Engineering, 1991
- Analysis and synthesis of neural networks with lower block triangular interconnecting structureIEEE Transactions on Circuits and Systems, 1990
- Back propagation fails to separate where perceptrons succeedIEEE Transactions on Circuits and Systems, 1989
- Neurocomputing, Volume 1Published by MIT Press ,1988
- Neural net pruning-why and howPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988