The effects of quantization on multilayer neural networks
- 1 January 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 6 (6) , 1446-1451
- https://doi.org/10.1109/72.471364
Abstract
The effect of weight quantization in multilayer neural networks is discussed. A method is derived by which one can predict the performance degradation at the output given the properties of the network and number of bits of quantization. Predictions from this method are evaluated against simulation results. An algorithm to decrease the noise at the output is presented and the results are compared with those above.Keywords
This publication has 11 references indexed in Scilit:
- Analog neural network circuits for ASIC fabricationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- On-chip learning in the analog domain with limited precision circuitsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Required dynamic range and accuracy of electronic synapses for character recognition applicationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Effects of Nonlinear Synapses on the Performance of Multilayer Neural NetworksNeural Computation, 1996
- Analysis of effects of quantisation in multilayer neural networks using statistical modelElectronics Letters, 1991
- An analysis on the performance of silicon implementations of backpropagation algorithms for artificial neural networksIEEE Transactions on Computers, 1991
- VLSI architectures for neural networksIEEE Micro, 1989
- Analog VLSI synaptic matrices as building blocks for neural networksIEEE Micro, 1989
- An electrically trainable artificial neural network (ETANN) with 10240 'floating gate' synapsesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Analogue circuits for variable-synapse electronic neural networksElectronics Letters, 1987