Feature Extraction Using Memristor Networks

Crossbar arrays of memristive elements are investigated for the implementation of dictionary learning and sparse coding of natural images. A winner-take-all training algorithm, in conjunction with Oja's rule, is used to learn an overcomplete dictionary of feature primitives that resemble Gabor...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2016-11, Vol.27 (11), p.2327-2336
Main Authors: Sheridan, Patrick M., Chao Du, Lu, Wei D.
Format: Article
Language:English
Subjects:
Analog computing
crossbar
Dictionaries
Feature extraction
Image coding
Image reconstruction
memristor
Memristors
Neurons
resistive switching
sparse coding
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Crossbar arrays of memristive elements are investigated for the implementation of dictionary learning and sparse coding of natural images. A winner-take-all training algorithm, in conjunction with Oja's rule, is used to learn an overcomplete dictionary of feature primitives that resemble Gabor filters. The dictionary is then used in the locally competitive algorithm to form a sparse representation of input images. The impacts of device nonlinearity and parameter variations are evaluated and a compensating procedure is proposed to ensure the robustness of the sparsification. It is shown that, with proper compensation, the memristor crossbar architecture can effectively perform sparse coding with distortion comparable with ideal software implementations at high sparsity, even in the presence of large device-to-device variations in the excess of 100%.
ISSN:2162-237X
2162-2388
DOI:10.1109/TNNLS.2015.2482220