Abstract—A novel neural networks model with quantum weights is present. Firstly, based on the information processing modes of biology neuron and quantum computing theory, a quantum neuron model is presented, which is composed of weighting, aggregating, activating, and inspiriting. Secondly the quantum neural networks model based on quantum neuron is constructed in which the input and the output are real vectors; the linked weight and the activation value are qubits. On the basic of the gradient descent algorithm, a learning algorithm of this model is proposed. It is shown that this algorithm is super-linearly convergent under certain conditions and can increase the probability of getting the global optimal solution. Finally, the availability of the model is illustrated in both convergence speed and convergence rate by two application examples of pattern recognition and function approximation.
Index Terms—Quantum computing, quantum neuron, quantum neural network, super-linear convergence
D. B. Mu is with the visit scholar with University of Waterloo, Canada (e-mail: d2mu@uwaterloo.ca).
Z. Y. Guan is with the Information Center of Daqing Oilfield, China (e-mail: guanzy@petrochina.com.cn).
H. Zhang is with the Oil and gas well production data management system (A2) of Daqing Oilfield Company. China (e-mail: zhang_hong_a@petrochina.com.cn).
[PDF]
Cite:Dianbao Mu, Zunyou Guan, and Hong Zhang, "Learning Algorithm and Application of Quantum Neural Networks with Quantum Weights," International Journal of Computer Theory and Engineering vol. 5, no. 5, pp. 788-792, 2013.
