Acceleration of Convolutional Networks Using Nanoscale Memristive Devices
Document Type
Conference Proceeding
Publication Date
1-1-2018
Abstract
We discuss a convolutional neural network for handwritten digit classification and its hardware acceleration as an inference engine using nanoscale memristive devices in the spike domain. We study the impact of device programming variability on the spiking neural network’s (SNN) inference accuracy and benchmark its performance with an equivalent artificial neural network (ANN). We demonstrate optimization strategies to implement these networks with memristive devices with an on-off ratio as low as 10 and only 32 levels of resolution. Further, close to baseline accuracies can be maintained for the networks even if such memristive devices are used to duplicate the pre-determined kernel weights to enable parallel execution of the convolution operation.
Identifier
85052887581 (Scopus)
ISBN
[9783319982038]
Publication Title
Communications in Computer and Information Science
External Full Text Location
https://doi.org/10.1007/978-3-319-98204-5_20
ISSN
18650929
First Page
240
Last Page
251
Volume
893
Grant
1710009
Fund Ref
National Science Foundation
Recommended Citation
Kulkarni, Shruti R.; Babu, Anakha V.; and Rajendran, Bipin, "Acceleration of Convolutional Networks Using Nanoscale Memristive Devices" (2018). Faculty Publications. 8967.
https://digitalcommons.njit.edu/fac_pubs/8967
