Multiplierless multilayer feedforward neural network design suitable for continuous input-output mapping
Hon Keung Kwan, C.Z. Tang · Electronics Letters · 1993
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.