Publication Details
Evolutionary Approximation and Neural Architecture Search
Mrázek Vojtěch, Ing., Ph.D. (DCSY)
Sekanina Lukáš, prof. Ing., Ph.D. (DCSY)
Approximate computing, Convolutional neural network, Cartesian genetic
programming, Neuroevolution, Energy efficiency
Automated neural architecture search (NAS) methods are now employed to routinely
deliver high-quality neural network architectures for various challenging data
sets and reduce the designers effort. The NAS methods utilizing multi-objective
evolutionary algorithms are especially useful when the objective is not only to
minimize the network error but also to reduce the number of parameters (weights)
or power consumption of the inference phase. We propose a multi-objective NAS
method based on Cartesian genetic programming for evolving convolutional neural
networks (CNN). The method allows approximate operations to be used in CNNs to
reduce the power consumption of a target hardware implementation. During the NAS
process, a suitable CNN architecture is evolved together with selecting
approximate multipliers to deliver the best trade-offs between accuracy, network
size, and power consumption. The most suitable 8 x N-bit approximate multipliers
are automatically selected from a library of approximate multipliers. Evolved
CNNs are compared with CNNs developed by other NAS methods on the CIFAR-10 and
SVHN benchmark problems.
@article{BUT179451,
author="Michal {Piňos} and Vojtěch {Mrázek} and Lukáš {Sekanina}",
title="Evolutionary Approximation and Neural Architecture Search",
journal="Genetic Programming and Evolvable Machines",
year="2022",
volume="23",
number="3",
pages="351--374",
doi="10.1007/s10710-022-09441-z",
issn="1389-2576",
url="https://link.springer.com/article/10.1007/s10710-022-09441-z"
}