Publication Details
Design of Power-Efficient Approximate Multipliers for Approximate Artificial Neural Networks
Sarwar Syed Shakib
Sekanina Lukáš, prof. Ing., Ph.D. (DCSY)
Vašíček Zdeněk, doc. Ing., Ph.D. (DCSY)
Roy Kaushik
Approximate computing, Neural networks, Logic synthesis, Low power, Genetic
programming
Artificial neural networks (NN) have shown a significant promise in difficult
tasks like image classification or speech recognition. Even well-optimized
hardware implementations of digital NNs show significant power consumption. It is
mainly due to non-uniform pipeline structures and inherent redundancy of numerous
arithmetic operations that have to be performed to produce each single output
vector. This paper provides a methodology for the design of well-optimized
power-efficient NNs with a uniform structure suitable for hardware
implementation. An error resilience analysis was performed in order to determine
key constraints for the design of approximate multipliers that are employed in
the resulting structure of NN. By means of a search based approximation method,
approximate multipliers showing desired tradeoffs between the accuracy and
implementation cost were created. Resulting approximate NNs, containing the
approximate multipliers, were evaluated using standard benchmarks (MNIST dataset)
and a real-world classification problem of Street-View House Numbers. Significant
improvement in power efficiency was obtained in both cases with respect to
regular NNs. In some cases, 91% power reduction of multiplication led to
classification accuracy degradation of less than 2.80%. Moreover, the paper
showed the capability of the back propagation learning algorithm to adapt with
NNs containing the approximate multipliers.
@inproceedings{BUT133493,
author="Vojtěch {Mrázek} and Syed Shakib {Sarwar} and Lukáš {Sekanina} and Zdeněk {Vašíček} and Kaushik {Roy}",
title="Design of Power-Efficient Approximate Multipliers for Approximate Artificial Neural Networks",
booktitle="Proceedings of the IEEE/ACM International Conference on Computer-Aided Design",
year="2016",
pages="811--817",
publisher="Association for Computing Machinery",
address="Austin, TX",
doi="10.1145/2966986.2967021",
isbn="978-1-4503-4466-1",
url="https://www.fit.vut.cz/research/publication/11142/"
}