Abstract:To enhance the approximation capability of neural networks,a quantum neural networks model is proposed whose input of each dimension is in discrete sequence. This model includes three layers,in which the hidden layer consists of quantum neurons,and the output layer consists of common neurons. The quantum neuron consists of the quantum rotation gates and the multi-qubits controlled-not gates. By using the information feedback of target qubit from output to input in multi-qubits controlled-not gate,the overall memory of input sequences is realized. The output of quantum neuron is obtained from the entanglements of multi-qubits in controlled-not gates. The learning algorithm is designed in detail according to the basis principles of quantum computation. The characteristics of input sequence can be effectively obtained from the width and the depth. The simulation results show that,when the input nodes and the length of the sequence satisfy a certain relations,the proposed model is superior to the common artificial neural networks.
李盼池,施光尧. 基于序列输入的量子神经网络模型及算法[J]. 模式识别与人工智能, 2013, 26(3): 247-253.
LI Pan-Chi,SHI Guang-Yao. Sequence-Input Based Quantum Neural Networks Model and Its Algorithm. , 2013, 26(3): 247-253.
[1] Tsoi A C,Back A D. Locally Recurrent Globally Feed forward Networks: A Critical Review of Architectures. IEEE Trans on Neural Networks,1994,5(2): 229-239 [2] Kak S. On Quantum Neural Computing. Information Sciences,1995,83(3): 143-160 [3] Purushpthaman G,Karayiannis N B. Quantum Neural Networks (QNNs) Inherently Fuzzy Feed forward Neural Networks. IEEE Trans on Neural Networks,1997,8(3): 679-693 [4] Ventura D,Marinez T. Quantum Associative Memory with Exponential Capacity // Proc of the International Joint Conference on Neural Networks. Anchorage,USA,1998: 509-513 [5] Narayanan A,Menneer T. Quantum Artificial Neural Network Architectures and Components. Information Sciences,2000,128(3/4): 231-255 [6] Xie Guangjun,Zhuang Zhenquan. Quantum Neural Networks. Computer Science,2001,28(7): 1-6 (in Chinese) (解光军,庄镇泉.量子神经网络.计算机科学,2001,28(7): 1-6) [7] Xie Guangjun,Fan Haiqiu,Cao Licheng. A Quantum Neural Computational Network Model. Journal of Fudan University: Natural Science,2004,43(5): 700-703 (in Chinese) (解光军,范海秋,操礼程.一种量子神经计算网络模型.复旦学报:自然科学版,2004,43(5): 700-703) [8] Xie Guangjun,Zhou Dian,Fan Haiqiu. A Neural Network Model Based on Quantum Gates Cell and Its Applications. Systems Engineering-Theory and Practice,2005,25(5): 113-117 (in Chinese) (解光军,周 典,范海秋.基于量子门组单元的神经网络及其应用.系统工程理论与实践,2005,25(5): 113-117) [9] Maeda M,Suenaga M,Miyajima H. Qubit Neuron According to Quantum Circuit for XOR Problem. Applied Mathematics and Computation,2007,185(2): 1015-1025 [10] Li Panchi,Li Shiyong. Learning Algorithm and Application of Quantum BP Neural Networks Based on Universal Quantum Gates. Journal of Systems Engineering and Electronics,2008,19(1): 167-174 [11] Adenilton J,Wilson R,Teresa B. Classical and Superposed Learning for Quantum Weightless Neural Networks. Neurocomputing,2012,75(1): 52-60 [12] Li Panchi,Song Kaoping,Yang Erlong. Quantum Neural Networks Model and Algorithm Based on the Quantum Gates Circuit. Control and Decision,2012,27(1): 143-146 (in Chinese) (李盼池,宋考平,杨二龙.基于量子门线路的量子神经网络模型及算法.控制与决策,2012,27(1): 143-146) [13] Li Panchi,Wang Haiying,Dai Qing,et al. Quantum Process Neural Networks Model Algorithm and Applications. Acta Physica Sinica,2012,61(16): 24-32 (in Chinese) (李盼池,王海英,戴 庆,等.量子过程神经网络模型算法及应用.物理学报,2012,61(16): 24-32)