A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms
1
Division of Electronics Engineering, Intelligent Robot Research Center, Chonbuk National University, Jeonbuk 54896, Korea
2
Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA
*
Author to whom correspondence should be addressed.
Academic Editor: Wendong Xiao
Sensors 2017, 17(1), 16; https://doi.org/10.3390/s17010016
Received: 29 September 2016
/
Revised: 9 December 2016
/
Accepted: 19 December 2016
/
Published: 23 December 2016
(This article belongs to the Section Sensor Networks)
A hybrid learning method of a software-based backpropagation learning and a hardware-based RWC learning is proposed for the development of circuit-based neural networks. The backpropagation is known as one of the most efficient learning algorithms. A weak point is that its hardware implementation is extremely difficult. The RWC algorithm, which is very easy to implement with respect to its hardware circuits, takes too many iterations for learning. The proposed learning algorithm is a hybrid one of these two. The main learning is performed with a software version of the BP algorithm, firstly, and then, learned weights are transplanted on a hardware version of a neural circuit. At the time of the weight transplantation, a significant amount of output error would occur due to the characteristic difference between the software and the hardware. In the proposed method, such error is reduced via a complementary learning of the RWC algorithm, which is implemented in a simple hardware. The usefulness of the proposed hybrid learning system is verified via simulations upon several classical learning problems.
View Full-Text
Keywords:
software-based learning; circuit-based learning; complementary learning; backpropagation; RWC
▼
Show Figures
Figure 1
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
MDPI and ACS Style
Yang, C.; Kim, H.; Adhikari, S.P.; Chua, L.O. A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms. Sensors 2017, 17, 16. https://doi.org/10.3390/s17010016
AMA Style
Yang C, Kim H, Adhikari SP, Chua LO. A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms. Sensors. 2017; 17(1):16. https://doi.org/10.3390/s17010016
Chicago/Turabian StyleYang, Changju, Hyongsuk Kim, Shyam P. Adhikari, and Leon O. Chua. 2017. "A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms" Sensors 17, no. 1: 16. https://doi.org/10.3390/s17010016
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
