Training layered perceptrons using low accuracy computation
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 554-559 vol.1
- https://doi.org/10.1109/ijcnn.1991.170458
Abstract
It is demonstrated that the random search approach to training layered perceptrons can be performed using low-accuracy computational precision, and therefore can be implemented using analog computational accuracy. In spite of their numerical stability, random search techniques suffer from ever-increasing search time as dimensionality grows. In response, the authors introduce a modified random search technique, improved bidirectional random optimization (IBRO), to improve the search accuracy per iteration. The proposed scheme should reduce overall search iterations dramatically. The authors compare the performance of IBRO with that of the bidirectional random optimization method through simulations.<>Keywords
This publication has 8 references indexed in Scilit:
- Optimizing Write Current and Write Power Consumption in Magnetoresistive Random Access Memories by Using Generalized Asteroid CurvesJapanese Journal of Applied Physics, 2007
- Nonlinear compensation for finite word length effects of an LMS echo canceller algorithm suitable for VLSI implementationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A new approach for finding the global minimum of error function of neural networksNeural Networks, 1989
- Minimization by Random Search TechniquesMathematics of Operations Research, 1981
- A modified convergence theorem for a random optimization methodInformation Sciences, 1977
- Adaptive Global Search by the Process of Competitive EvolutionIEEE Transactions on Systems, Man, and Cybernetics, 1975
- Random search techniques for optimization problemsAutomatica, 1963
- Recent Advances in Finding Best Operating ConditionsJournal of the American Statistical Association, 1953