A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms

Sensors

Leon O. Chua¹  Changju Yang²  Shyam Prasad Adhikari²  Hyongsuk Kim² 

[1] Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, USA;Division of Electronics Engineering, Intelligent Robot Research Center, Chonbuk National University, Jeonbuk 54896, Korea;

关键词: software-based learning;    circuit-based learning;    complementary learning;    backpropagation;    RWC;   

DOI  :  10.3390/s17010016

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown