量子小波神经网络及其在漏钢预报中的应用

Quantum wavelet neural networks and its application in breakout prediction

针对传统神经网络收敛速度慢,收敛精度低,以及用于模式识别泛化能力差的问题。提出了将量子神经网络与小波理论相结合的量子小波神经网络模型。该模型隐层量子神经元采用小波基函数的线性叠加作为激励函数,称之为多层小波激励函数,这样隐层神经元既能表示更多的状态和量级,又能提高网络收敛精度和速度。给出了网络学习算法。并以之在漏钢预报波形识别中的应用验证了该模型和学习算法的有效性。

In order to overcome the problems of slow speed and low accuracy of convergence and the shortcomings of generalization ability for pattern recognition of the traditional neural networks,the quantum neural network combines with wavelet theory form the wavelet quantum neural network model is given.The quantum neurons of hidden layer of the model using a linear superposition of wavelet function as incentive function,called multi-wavelet incentive function,such hidden layer neurons not only can express more of the status and magnitude,but also can improve network speed and accuracy of convergence.The same time this paper presents a learning algorithm.And the validity of the model and the study algorithm are proved by its application in recognition of breakout prediction.