Multiplierless multilayer feedforward neural network design using quantised neurons

Electronics Letters

Volumn 38, Issue 13, 2002, Pages 645-646

  Kwan, H K ^a   Tang, C Z ^a  

^a UNIVERSITY OF WINDSOR   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; BACKPROPAGATION; FUNCTIONS; SIMULATION; VLSI CIRCUITS;

BACKPROPAGATION ALGORITHM; BIPOLAR SIGMOID ACTIVATION FUNCTION; QUANTISED NEURONS;

FEEDFORWARD NEURAL NETWORKS;

EID: 0037142433     PISSN: 00135194     EISSN: None     Source Type: Journal    
DOI: 10.1049/el:20020465     Document Type: Article

References (8)

1. The digi-neocognitron: A digital neocognitron neural network model for VLSI
2. Tutorial: Digital neurocomputing for signal/image processing
3. Integer-weight approximation of continuous-weight multilayer feedforward nets
4. Fast neural networks without multipliers
5. Designing multilayer feedforward neural networks using simplified sigmoid activation functions and one-powers-of-two weights
6. Multilayer feedforward neural networks with single powers-of-two weights
7. Parameter effects on convergence speed and generalization capability of backpropagation algorithm