TY - GEN
T1 - Adder-Only Convolutional Neural Network with Binary Input Image
AU - Palaria, Mayank
AU - Sanjeet, Sai
AU - Sahoo, Bibhu Datta
AU - Fujita, Masahiro
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/8
Y1 - 2019/8
N2 - Convolutional neural networks (CNNs) have performed exceptionally well on a variety of image classification tasks but need significant amount of memory and computational resources. In this paper, we propose an adder-only CNN (AO-CNN) inference engine, that has its weights and/or outputs at each layer reduced to either powers of two or zero, thus replacing the multiplication operations with a simple right or left shift and hence reducing the computation significantly. The proposed AO-CNN architecture, demonstrated using three sets of data-sets, viz., MNIST, EMNIST, and SVHN, performs with ≈ 80% accuracy or more, while using minimal hardware and taking only binary input images, i.e., 1 and 0. This could pave the way for realization of image-sensors with 1-bit resolution images and the corresponding CNN based classification engine being integrated into low-power internet-of-things (IoT) devices.
AB - Convolutional neural networks (CNNs) have performed exceptionally well on a variety of image classification tasks but need significant amount of memory and computational resources. In this paper, we propose an adder-only CNN (AO-CNN) inference engine, that has its weights and/or outputs at each layer reduced to either powers of two or zero, thus replacing the multiplication operations with a simple right or left shift and hence reducing the computation significantly. The proposed AO-CNN architecture, demonstrated using three sets of data-sets, viz., MNIST, EMNIST, and SVHN, performs with ≈ 80% accuracy or more, while using minimal hardware and taking only binary input images, i.e., 1 and 0. This could pave the way for realization of image-sensors with 1-bit resolution images and the corresponding CNN based classification engine being integrated into low-power internet-of-things (IoT) devices.
UR - https://www.scopus.com/pages/publications/85075010022
U2 - 10.1109/MWSCAS.2019.8885354
DO - 10.1109/MWSCAS.2019.8885354
M3 - Conference contribution
AN - SCOPUS:85075010022
T3 - Midwest Symposium on Circuits and Systems
SP - 319
EP - 322
BT - 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems, MWSCAS 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 62nd IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2019
Y2 - 4 August 2019 through 7 August 2019
ER -