Design of memristor-based image convolution calculation in convolutional neural network Academic Article

abstract

• 2016, The Natural Computing Applications Forum. In this paper, an architecture based on memristors is proposed to implement image convolution computation in convolutional neural networks. This architecture could extract different features of input images when using different convolutional kernels. Bipolar memristors with threshold are employed in this work, which vary their conductance values under different voltages. Various kernels are needed to extract information of input images, while different kernels contain different weights. The memristances of bipolar memristors with threshold are convenient to be varied and kept, which make them suitable to act as the weights of kernels. The performances of the design are verified by simulation results.

authors

• Huang, Tingwen

published proceedings

• NEURAL COMPUTING & APPLICATIONS

author list (cited authors)

• Zeng, X., Wen, S., Zeng, Z., & Huang, T.

citation count

• 45

complete list of authors

• Zeng, Xiaofen||Wen, Shiping||Zeng, Zhigang||Huang, Tingwen

publication date

• July 2018

publisher

• Springer Nature  Publisher

published in

• Neural Computing and Applications  Journal

keywords

• Convolutional Neural Network
• Image Convolution Computation
• Memristor

Digital Object Identifier (DOI)

• 10.1007/s00521-016-2700-2

start page

• 503

end page

• 508

volume

• 30

issue

• 2

URL

• http://dx.doi.org/10.1007/s00521-016-2700-2