Training an Artificial Neural Network with Op-amp Integrators Based Analog Circuits

Weiliang Liu; Zhan Li; Shengri Xue; Xuebo Yang; Weiyang Lin

doi:10.1109/GNCC42960.2018.9018997

Training an Artificial Neural Network with Op-amp Integrators Based Analog Circuits

Weiliang Liu
, Zhan Li
, Shengri Xue
, Xuebo Yang
, Weiyang Lin

School of Astronautics

Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The artificial neural network (ANN) has shown the effectiveness in unmanned systems and many other fields. Training an ANN with CPUs or other digital circuits can take a long time. And thus some analog neural network models have been composed to utilize the inherent advantage of analog circuits. However there are some problems in these models when considering about the flexibility and the speed. In this paper, we use op-amp integrators to store the weights of an analog ANN, and use the feedback of the circuit to train the network. It is easy to hold or change the weights in our circuit and the training of a sample can be automatically done quickly. The circuit only supports the ANN with one output in this paper. Besides more possible utilizations of the circuit are also proposed.

Original language	English
Title of host publication	2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538611715
DOIs	https://doi.org/10.1109/GNCC42960.2018.9018997
State	Published - Aug 2018
Event	2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018 - Xiamen, China Duration: 10 Aug 2018 → 12 Aug 2018

Publication series

Name	2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018

Conference

Conference	2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018
Country/Territory	China
City	Xiamen
Period	10/08/18 → 12/08/18

Access to Document

10.1109/GNCC42960.2018.9018997

Cite this

Liu, W., Li, Z., Xue, S., Yang, X., & Lin, W. (2018). Training an Artificial Neural Network with Op-amp Integrators Based Analog Circuits. In 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018 Article 9018997 (2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GNCC42960.2018.9018997

@inproceedings{57f8d7e41d54407bbbe713157a3189fb,

title = "Training an Artificial Neural Network with Op-amp Integrators Based Analog Circuits",

abstract = "The artificial neural network (ANN) has shown the effectiveness in unmanned systems and many other fields. Training an ANN with CPUs or other digital circuits can take a long time. And thus some analog neural network models have been composed to utilize the inherent advantage of analog circuits. However there are some problems in these models when considering about the flexibility and the speed. In this paper, we use op-amp integrators to store the weights of an analog ANN, and use the feedback of the circuit to train the network. It is easy to hold or change the weights in our circuit and the training of a sample can be automatically done quickly. The circuit only supports the ANN with one output in this paper. Besides more possible utilizations of the circuit are also proposed.",

author = "Weiliang Liu and Zhan Li and Shengri Xue and Xuebo Yang and Weiyang Lin",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018 ; Conference date: 10-08-2018 Through 12-08-2018",

year = "2018",

month = aug,

doi = "10.1109/GNCC42960.2018.9018997",

language = "英语",

series = "2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018",

address = "美国",

}

Liu, W, Li, Z, Xue, S, Yang, X & Lin, W 2018, Training an Artificial Neural Network with Op-amp Integrators Based Analog Circuits. in 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018., 9018997, 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018, Institute of Electrical and Electronics Engineers Inc., 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018, Xiamen, China, 10/08/18. https://doi.org/10.1109/GNCC42960.2018.9018997

Training an Artificial Neural Network with Op-amp Integrators Based Analog Circuits. / Liu, Weiliang; Li, Zhan; Xue, Shengri et al.
2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. 9018997 (2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Training an Artificial Neural Network with Op-amp Integrators Based Analog Circuits

AU - Liu, Weiliang

AU - Li, Zhan

AU - Xue, Shengri

AU - Yang, Xuebo

AU - Lin, Weiyang

PY - 2018/8

Y1 - 2018/8

N2 - The artificial neural network (ANN) has shown the effectiveness in unmanned systems and many other fields. Training an ANN with CPUs or other digital circuits can take a long time. And thus some analog neural network models have been composed to utilize the inherent advantage of analog circuits. However there are some problems in these models when considering about the flexibility and the speed. In this paper, we use op-amp integrators to store the weights of an analog ANN, and use the feedback of the circuit to train the network. It is easy to hold or change the weights in our circuit and the training of a sample can be automatically done quickly. The circuit only supports the ANN with one output in this paper. Besides more possible utilizations of the circuit are also proposed.

AB - The artificial neural network (ANN) has shown the effectiveness in unmanned systems and many other fields. Training an ANN with CPUs or other digital circuits can take a long time. And thus some analog neural network models have been composed to utilize the inherent advantage of analog circuits. However there are some problems in these models when considering about the flexibility and the speed. In this paper, we use op-amp integrators to store the weights of an analog ANN, and use the feedback of the circuit to train the network. It is easy to hold or change the weights in our circuit and the training of a sample can be automatically done quickly. The circuit only supports the ANN with one output in this paper. Besides more possible utilizations of the circuit are also proposed.

UR - https://www.scopus.com/pages/publications/85082467432

U2 - 10.1109/GNCC42960.2018.9018997

DO - 10.1109/GNCC42960.2018.9018997

M3 - 会议稿件

AN - SCOPUS:85082467432

T3 - 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018

BT - 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018

Y2 - 10 August 2018 through 12 August 2018

ER -

Liu W, Li Z, Xue S, Yang X , Lin W. Training an Artificial Neural Network with Op-amp Integrators Based Analog Circuits. In 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018. Institute of Electrical and Electronics Engineers Inc. 2018. 9018997. (2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018). doi: 10.1109/GNCC42960.2018.9018997

Training an Artificial Neural Network with Op-amp Integrators Based Analog Circuits

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this