Los Angeles, CA
March 31, 2009 to April 2, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CSIE.2009.601
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.
integer weights, genetic algorithm, neural network, embedded system, real time process
Jian Bao, Bin Zhou, Yi Yan, "A Genetic-Algorithm-Based Weight Discretization Paradigm for Neural Networks", CSIE, 2009, 2009 WRI World Congress on Computer Science and Information Engineering, CSIE, 2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009, pp. 655-659, doi:10.1109/CSIE.2009.601