[10p-S223-1~11] 11.5 Junction and circuit fabrication process, digital applications

[10p-S223-5] Design and Evaluation of Arbitrary Output Logic Gate by Superconducting Neural Network Using Quantum Flux Parametron

〇(B)Daiki Yamaguchi¹, Yuki Yamanashi^1,2, Naoki Takeuchi², Nobuyuki Yoshikawa^1,2 (1.Dept. of Electrical and Computer Eng., Yokohama Natl. Univ., 2.IAS, Yokohama Natl. Univ.)

Keywords:neural network, superconductor

An artificial neural network (ANN) is a circuit that imitates the brain of a human, which is effective for pattern recognition and filtering, and so on. The ANN implemented by the semiconductor circuit consumes a lot of power because of the circuit scale increases due to the parallel processing of the ANN. Because a superconducting circuit can operate at the high frequency with low power consumption, it is attractive for realization of energy-efficient ANNs. In this study, we designed a simple superconducting ANN that performs arbitrary 2-input logic operation using the quantum flux parametron (QFP) and dc-superconducting quantum interference device (SQUID).