2020年
Learning Neural Circuit by AC Operation and Frequency Signal Output
Computer and Information Science, ICIS2019 best paper,
- ,
- ,
- 巻
- 849
- 号
- 開始ページ
- 15
- 終了ページ
- 30
- 記述言語
- 英語
- 掲載種別
- 論文集(書籍)内論文
- DOI
- 10.1007/978-3-030-25213-7_2
- 出版者・発行元
- Springer International Publishing
© Springer Nature Switzerland AG 2020. In the machine learning field, many application models such as pattern recognition or event prediction have been proposed. Neural Network is a typically basic method of machine learning. In this study, we used analog electronic circuits using alternative current to realize the neural network learning model. These circuits are composed by a rectifier circuit, Voltage-Frequency converter, amplifier, subtract circuit, additional circuit and inverter. The connecting weights describe the frequency converted to direct current from alternating current by a rectifier circuit. This model’s architecture is on the analog elements. The learning time and working time are very short because this system is not depending on clock frequency. Moreover, we suggest the realization of the deep learning model regarding the proposed analog hardware neural circuit.
- リンク情報
- ID情報
-
- DOI : 10.1007/978-3-030-25213-7_2
- ISSN : 1860-949X
- eISSN : 1860-9503
- DBLP ID : conf/ACISicis/KawaguchiIU19
- SCOPUS ID : 85070509998