Presentation | 2020-01-17 [Poster Presentation] Investigation of neuron with sigmoid activation function for quantum-flux-parametron-based neural network Daiki Yamaguchi, Yuki Yamanashi, Nobuyuki Yoshikawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | An ANN is a circuit that imitates the brain of a human, which is effective for pattern recognition and ?ltering, and so on. A superconducting circuit can operate at the high fre-quency with low power consumption, it is attractive for realization of energy-ef?cient ANNs. In order to perform ANN learning, it is necessary for the activation function of neurons in the middle layer to have characteristics like sigmoid/hyperbolic tangent function. The rf-superconducting quantum interference device (rf-SQUID) is composed of a supercon-ducting loop including a Josephson junction and an inductance, and when a magnetic ?ux is applied to the circuit, a circular current is generated as if sine is inclined. Applying the cir-cuit of rf-SQUID, it is known that the input/output relationship of magnetic ?ux has charac-teristics close to the sigmoid/hyperbolic tangent function. In this study, we designed a neuron with a hyperbolic tangent activation function using the AIST fabrication process. Fur-thermore, we investigated tuning method of the quantum-flux-parametron-based supercon-ducting neural network toward its learning. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | rf-SQUIDANNsigmoidhyperbolic tangent |
Paper # | SCE2019-60 |
Date of Issue | 2020-01-09 (SCE) |
Conference Information | |
Committee | SCE |
---|---|
Conference Date | 2020/1/16(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Satoshi Kohjiro(AIST) |
Vice Chair | |
Secretary | (Yokohama National Univ.) |
Assistant | Hiroyuki Akaike(Daido Univ.) |
Paper Information | |
Registration To | Technical Committee on Superconductive Electronics |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | [Poster Presentation] Investigation of neuron with sigmoid activation function for quantum-flux-parametron-based neural network |
Sub Title (in English) | |
Keyword(1) | rf-SQUIDANNsigmoidhyperbolic tangent |
1st Author's Name | Daiki Yamaguchi |
1st Author's Affiliation | Yokohama National University(Yokohama Natl. Univ.) |
2nd Author's Name | Yuki Yamanashi |
2nd Author's Affiliation | Yokohama National University(Yokohama Natl. Univ.) |
3rd Author's Name | Nobuyuki Yoshikawa |
3rd Author's Affiliation | Yokohama National University(Yokohama Natl. Univ.) |
Date | 2020-01-17 |
Paper # | SCE2019-60 |
Volume (vol) | vol.119 |
Number (no) | SCE-369 |
Page | pp.pp.125-127(SCE), |
#Pages | 3 |
Date of Issue | 2020-01-09 (SCE) |