【摘要】 提出了一种用于多层前馈神经网络训练的新算法，它把遗传算法与自适应共轭梯度学习算法集成起来。这种并行混合学习算法已经在多指令流多数据流（ＭＩＭＤ）平台实现。通过把该算法用于一个图像识别问题，对它的性能进行了评估。文中还显示了所提出的并行混合神经网络学习算法良好的收敛性。更多还原

【Abstract】 A new algorithm is presented for training of multilayer feed forward networks by integrating a genetic algorithm with an adaptive conjugate gradient neural network learning algorithm.The parallel hybrid algorithm is implemented on an MIMD Platform.The performance of the algorithm is evaluated by applying it to a example in the domain of imagerecognition.The parallel hybrid neural network learing algorithm presented in this Paper has a superior convergence property.更多还原