[期刊论文]

出版年：2003

An integrated approach of magnified gradient function and weight evolution with deterministic perturbation to improve the performance of back-propagation learning is proposed. Simulation results show that, in terms of the convergence rate and the percentage of global convergence, the integrated approach always outperforms the other traditional methods.

backpropagation; convergence; back-propagation algorithm; backpropagation learning; convergence rate; deterministic perturbation; global convergence; magnified gradient function; performance improvement; weight evolution