Fast neural networks without multipliers
- 1 January 1993
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 4 (1) , 53-62
- https://doi.org/10.1109/72.182695
Abstract
Multilayer perceptrons (MLPs) with weight values restricted to powers of two or sums of powers of two are introduced. In a digital implementation, these neural networks do not need multipliers but only shift registers when computing in forward mode, thus saving chip area and computation time. A learning procedure, based on backpropagation, is presented for such neural networks. This learning procedure requires full real arithmetic and therefore must be performed offline. Some test cases are presented, concerning MLPs with hidden layers of different sizes, on pattern recognition problems. Such tests demonstrate the validity and the generalization capability of the method and give some insight into the behavior of the learning algorithm.Keywords
This publication has 12 references indexed in Scilit:
- FIR filter design and implementation with powers-of-two coefficientsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- The digi-neocognitron: a digital neocognitron neural network model for VLSIIEEE Transactions on Neural Networks, 1992
- Weight Perturbation: An Optimal Architecture and Learning Technique for Analog VLSI Feedforward and Recurrent Multilayer NetworksNeural Computation, 1991
- Analysis of effects of quantisation in multilayer neural networks using statistical modelElectronics Letters, 1991
- Multi-layer perceptrons with discrete weightsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Accelerating the convergence of the back-propagation methodBiological Cybernetics, 1988
- A simple design of FIR filters with powers-of-two coefficientsIEEE Transactions on Circuits and Systems, 1988
- Increased rates of convergence through learning rate adaptationNeural Networks, 1988
- Design of cascade form FIR filters with discrete valued coefficientsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987