多层前向神经网络的自适应遗传算法训练

多层前向神经网络的自适应遗传算法训练 An Efficient Improved Adaptive Genetic Algorithm for Training Layered Feedforward Neural Networks 王新苗 WANG Xin\|miao 1 first-author 晏蒲柳 YAN Pu\|liu 1 黄天锡 HUANG Tian\|xi 1 武汉大学电子信息学学院,武汉,430072 武汉大学电子信息学学院,武汉,430072 College of Electronic Information ,Wuhan University College of Electronic Information ,Wuhan University 提出了一种改进的自适应遗传算法 Ｉ Ａ Ｇ Ａ，它利用网络结构的特点，采用前向自适应技术，实现对神经网络的有效训练．实验表明，该算法优于 Ｂ Ｐ算法、标准遗传算法 Ｂ Ｇ Ａ 和普通自适应遗传算法 Ａ Ｇ Ａ，网络训练质量和效率都有很大提高 Layered feedforward neural network training algorithm based on traditional BP algorithm may lead to entrapment in local optimum, and has the defects such as slow convergent speed and unsatisfied dynamic character which reduce the study ability of the network. This paper presents an improved adaptive genetic algorithm （IAGA） for training the neural network efficiently that uses a forward adaptive technique and takes the advantages of the network architecture. The experimental results show that our algorithm outperforms BP algorithm, BGA algorithm and AGA algorithm, and the dynamic character, training accuracy and efficiency proved greatly. 神经网络 遗传算法 自适应 neural network genetic algorithm adaptive TP18 国家自然科学基金(61672102) 1999-03-01 2021-04-01 3