This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2009 WRI World Congress on Computer Science and Information Engineering
A Genetic-Algorithm-Based Weight Discretization Paradigm for Neural Networks
Los Angeles, California USA
March 31-April 02
ISBN: 978-0-7695-3507-4
The traditional neural networks with continuous weights easy to implement in software might often be very burdensome in the embedded hardware systems and therefore more costly. Hardware-friendly neural networks are essential to ensure the functionality and effectiveness of the embedded implementation. To achieve this aim, A GA-based algorithm for training neural networks with discrete weights and quantized on-linear activation function is presented in this paper. The performance of this procedure is evaluated by comparing it with multi-threshold method and continuous discrete learning method based on computing the gradient of the error function, and the simulation results show this new learning algorithm outperforms the other two greatly in convergence and generalization.
Index Terms:
integer weights, genetic algorithm, neural network, embedded system, real time process
Citation:
Jian Bao, Bin Zhou, Yi Yan, "A Genetic-Algorithm-Based Weight Discretization Paradigm for Neural Networks," csie, vol. 4, pp.655-659, 2009 WRI World Congress on Computer Science and Information Engineering, 2009
Usage of this product signifies your acceptance of the Terms of Use.