CAJ | 학술논문

人工神经网络在很多领域有着成功的应用。神经网络参数估计有许多训练算法，BP算法是前向多层神经网络的典型算法，但BP算法有时会陷入局部最小解。进化规划是一种随机优化技术，它可以发现全局最优解。文章介绍了进化规划在前向多层神经网络参数估计中的应用，结合具体例子给出了算法实现的具体操作步骤和实验结果。实验数据表明采用进化规划得到的网络参数是最优的，神经网络的性能优于基于BP算法的神经网络性能。
인공신경망락재흔다영역유착성공적응용。신경망락삼수고계유허다훈련산법，BP산법시전향다층신경망락적전형산법，단BP산법유시회함입국부최소해。진화규화시일충수궤우화기술，타가이발현전국최우해。문장개소료진화규화재전향다층신경망락삼수고계중적응용，결합구체례자급출료산법실현적구체조작보취화실험결과。실험수거표명채용진화규화득도적망락삼수시최우적，신경망락적성능우우기우BP산법적신경망락성능。
Artificial neural networks were successfully applied to solve actual problems in many areas. There are a few training algorithms for parameter estimation of neural networks,in which Back Propagation(BP)algorithm is the typical algorithm for feed-forward multi-layer neural networks. However,BP algorithm sometimes traps into the local minimum.Evolutionary Programming(EP),a multi-agent stochastic optimization technique,can lead to global optimal solutions for complex problems. In this paper,an application of EP to parameter estimation for feed-forward multi-layer neural networks is introduced. An example of curve fitting is presented,and the steps of EP realization and experimental results are given. Experimental results have shown that parameters of the network obtained by EP can be ensured to be optimal, and the performance of the network is better than that of the network based on BP algorithm.