TY - GEN
T1 - PredictiveNet
T2 - 50th IEEE International Symposium on Circuits and Systems, ISCAS 2017
AU - Lin, Yingyan
AU - Sakr, Charbel
AU - Kim, Yongjune
AU - Shanbhag, Naresh
N1 - Funding Information:
ACKNOWLEDGMENT This work was supported in part by Systems on Nanoscale Information fabriCs (SONIC), one of the six SRC STARnet Centers, sponsored by MARCO and DARPA.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/9/25
Y1 - 2017/9/25
N2 - Convolutional neural networks (CNNs) have gained considerable interest due to their record-breaking performance in many recognition tasks. However, the computational complexity of CNNs precludes their deployments on power-constrained embedded platforms. In this paper, we propose predictive CNN (PredictiveNet), which predicts the sparse outputs of the non-linear layers thereby bypassing a majority of computations. PredictiveNet skips a large fraction of convolutions in CNNs at runtime without modifying the CNN structure or requiring additional branch networks. Analysis supported by simulations is provided to justify the proposed technique in terms of its capability to preserve the mean square error (MSE) of the nonlinear layer outputs. When applied to a CNN for handwritten digit recognition, simulation results show that PredictiveNet can reduce the computational cost by a factor of 2.9χ compared to a state-of-the-art CNN, while incurring marginal accuracy degradation.
AB - Convolutional neural networks (CNNs) have gained considerable interest due to their record-breaking performance in many recognition tasks. However, the computational complexity of CNNs precludes their deployments on power-constrained embedded platforms. In this paper, we propose predictive CNN (PredictiveNet), which predicts the sparse outputs of the non-linear layers thereby bypassing a majority of computations. PredictiveNet skips a large fraction of convolutions in CNNs at runtime without modifying the CNN structure or requiring additional branch networks. Analysis supported by simulations is provided to justify the proposed technique in terms of its capability to preserve the mean square error (MSE) of the nonlinear layer outputs. When applied to a CNN for handwritten digit recognition, simulation results show that PredictiveNet can reduce the computational cost by a factor of 2.9χ compared to a state-of-the-art CNN, while incurring marginal accuracy degradation.
UR - http://www.scopus.com/inward/record.url?scp=85032710674&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85032710674&partnerID=8YFLogxK
U2 - 10.1109/ISCAS.2017.8050797
DO - 10.1109/ISCAS.2017.8050797
M3 - Conference contribution
AN - SCOPUS:85032710674
T3 - Proceedings - IEEE International Symposium on Circuits and Systems
BT - IEEE International Symposium on Circuits and Systems
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 28 May 2017 through 31 May 2017
ER -