欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为提高神经网络的逼近能力,提出一种基于受控Hadamard门设计的量子神经网络模型及算法.该模型输入为多维离散序列,可用矩阵描述,行数为输入节点数,列数为序列长度.模型为3层结构,隐层为量子神经元,输出层为普通神经元.量子神经元由量子旋转门和多位受控Hadamard门组成,利用多位受控Hadamard门中目标量子位的输出向输入端的反馈,实现对输入序列的整体记忆,利用受控Hadamard门中控制位和目标位之间的受控关系获得量子神经元的输出.基于量子计算理论设计了该模型的学习算法.该模型可高效地获取输入序列的特征.实验结果表明,当输入节点数和序列长度满足一定关系时,该模型明显优于普通BP神经网络.
英文摘要：
To enhance the approximation capability of neural network, a quantum neural network model based on the controlled-Hadamard gates is proposed. This model takes a multi-dimensional discrete sequence as the input, which can be described by a matrix where the number of rows denotes the number of input nodes, and the number of columns denotes the length of discrete sequence. This model consists of three layers, 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-Hadamard gates. Using the information feedback of target qubit from output to input in multi-qubits controlled Hadamard gates, the overall memory of input sequence is realized. The output of quantum neuron is obtained from the controlled relationship between the control bits and target bit of controlled-Hadamard 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. The experimental results show that, when the input nodes and the length of the sequence satisfy certain relations, the proposed model is obviously superior to the common BP neural network.
同期刊论文项目
同项目期刊论文
Quantum ant colony optimization algorithm based on Bloch spherical search (SCI: 000309320500002; EI:
期刊信息
位置：