Multiplierless multilayer feedforward neural network design suitable for continuous input-output mapping
- 8 July 1993
- journal article
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 29 (14) , 1259-1260
- https://doi.org/10.1049/el:19930841
Abstract
A method for designing a multiplierless multilayer feed-forward neural network (MFNN) suitable for continuous input–output mapping is presented. When tested with noisy vectors, the network can retain a similar recall accuracy as the corresponding MFNN with continuous weights. The advantages of the design method include faster computational speed and reduced digital hardware cost.Keywords
This publication has 2 references indexed in Scilit:
- Systolic architectures for Hopfield network, BAM and multi-layer feed-forward networkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Parallel architectures for artificial neural netsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988