Presentation Information

[16a-K209-6]Design of ReLU Output Characteristic Circuit for Superconducting Neural Networks

〇Yuto Ueno1, Yuki Hironaka2, Nobuyuki Yoshikawa1,2, Yuki Yamanashi1,2 (1.Yokohama National Univ., 2.Yokohama National Univ. IAS)

Keywords:

Single Flux Quantumn Circuit,Activate Fanction

The design of a high-speed, low-power artificial neural network (ANN) dedicated circuit based on single-flux quantum technology has been investigated. To enhance the efficiency and versatility of ANN-specific circuits, the ReLU activation function was employed. The design incorporates a Delay Flip-Flop with escape functionality and a Delay Flip-Flop with a reset function. Simulation results confirmed the successful attainment of ideal outputs.

Comment

To browse or post comments, you must log in.Log in