Přístupnostní navigace
E-application
Search Search Close
Publication detail
PIŇOS, M. MRÁZEK, V. SEKANINA, L.
Original Title
Evolutionary Approximation and Neural Architecture Search
Type
journal article in Web of Science
Language
English
Original Abstract
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.
Keywords
Approximate computing, Convolutional neural network, Cartesian genetic programming, Neuroevolution, Energy efficiency
Authors
PIŇOS, M.; MRÁZEK, V.; SEKANINA, L.
Released
10. 6. 2022
ISBN
1389-2576
Periodical
Genetic Programming and Evolvable Machines
Year of study
23
Number
3
State
United States of America
Pages from
351
Pages to
374
Pages count
24
URL
https://link.springer.com/article/10.1007/s10710-022-09441-z
BibTex
@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" }