基于量子免疫克隆算法的神经网络优化方法

Quantum-inspired clonal algorithm based method for optimizing neural networks

为降低神经网络的冗余连接及不必要的计算代价,将量子免疫克隆算法应用于神经网络的优化过程,通过产生具有稀疏度的权值来优化神经网络结构。算法能够有效删除神经网络中的冗余连接和隐层节点,并同时提高神经网络的学习效率、函数逼近精度和泛化能力。该算法已应用于秦始皇帝陵博物院野外文物安防系统。经实际检验,算法提高了目标分类概率,降低了误报率。

In order to reduce the redundant connections and unnecessary computing cost, quantum-inspired clonal algorithm was applied to optimize neural networks. By generating neural network weights which have certain sparse ratio, the algorithm not only effectively removed redundant neural network connections and hidden layer nodes, but also improved the learning efficiency of neural network, the approximation of function accuracy and generalization ability. This method had been applied to wild relics security system of Emperor Qinshihuang＇s mausoleum site museum, and the results show that the method can raise the probability of target classification and reduce the false alarm rate.