基于STDP规则和忆阻桥突触的神经网络及图像处理

忆阻器是具有记忆和类突触特性的非线性电路元件.基于此特性,文中提出了一个基于STDP（spike-time-dependent plasticity）学习规则的忆阻桥突触电路,它具有可以作为人工神经网络突触的优势.根据此优势,将这个新的电路与其他电路和网络结合,构成全新的电路和网络.首先将该忆阻桥突触电路和3个附加的晶体管结合在一起,实现神经网络的突触运算,并构建完整的忆阻桥突触神经网络.然后再将它与细胞神经网络结合用于图像去噪、边缘提取、角检测和汉字识别.最后,通过一系列的仿真实验证实了该方案的可行性,说明基于STDP学习规则的忆阻桥突触神经网络更具仿生特性,而且集成度更高、模板更易更换,有望解决实时的复杂的智能问题.

Neural networks based on STDP rules and memristor bridge synapses with applications in image processing

Memristor is a nonlinear circuit element which has property of memory and the similar synapse characteristic. Based on these properties, we presents a memristor bridge synaptic circuit based on the STDP （spike-time-dependent plasticity） learning rule which has an advantage that can be used as a synapse in the artificial neural network. According to the advantage, we combine the new circuit with other circuits and networks and the bran-new circuits and networks are constructed. Firstly, we combine the memristor bridge synaptic circuit with three additional transistor components and the synaptic calculation of the neural network is realized, and then the complete memristor bridge synaptic neural network is constructed. Secondly, we combine the cellular neural network with it and can be used in image denoising, edge extraction, corner detection and Chinese character recognition. Finally, the feasibility of the proposed method is proved by the a series of the simulation experiments, and the memristor bridge synaptic neural network based on the STDP learning rule has more bionic feasibility, more integrated and more easy to replace the template are demonstrated, and it is hopeful to solve the real-time complex intelligent problems.