An improved superconducting neural circuit and its application for a neural network solving a combinatorial optimization problem

11th European Conference on Applied Superconductivity

Onomi, T.^1 ; Nakajima, K.^1

Research Institute of Electrical Communication, Tohoku University, 2-1-1 Katahira, Aoba-ku, Miyagi, Sendai

980-8577, Japan^1

关键词: Combinatorial optimization problems;    Hopfield type neural networks;    Improved designs;    ITS applications;    N-queens problems;    Neuron circuits;    Single junction;    Threshold characteristics;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/507/4/042029/pdf
DOI  :  10.1088/1742-6596/507/4/042029

来源: IOP

【 摘 要 】

We have proposed a superconducting Hopfield-type neural network for solving the N-Queens problem which is one of combinatorial optimization problems. The sigmoid-shape function of a neuron output is represented by the output of coupled SQUIDs gate consisting of a single-junction and a double-junction SQUIDs. One of the important factors for an improvement of the network performance is an improvement of a threshold characteristic of a neuron circuit. In this paper, we report an improved design of coupled SQUID gates for a superconducting neural network. A step-like function with a steep threshold at a rising edge is desirable for a neuron circuit to solve a combinatorial optimization problem. A neuron circuit is composed of two coupled SQUIDs gates with a cascade connection in order to obtain such characteristics. The designed neuron circuit is fabricated by a 2.5 kA/cm2Nb/AlOx/Nb process. The operation of a fabricated neuron circuit is experimentally demonstrated. Moreover, we discuss about the performance of the neural network using the improved neuron circuits and delayed negative self-connections.