Detail publikačního výsledku

Multi-objective Evolutionary Neural Architecture Search for Hailo Accelerators

NEPRAŠ, D.; SEKANINA, L.

Originální název

Multi-objective Evolutionary Neural Architecture Search for Hailo Accelerators

Anglický název

Multi-objective Evolutionary Neural Architecture Search for Hailo Accelerators

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

A multi-objective, hardware-aware Neural Architecture Search (NAS) framework is introduced and evaluated for efficient design of convolutional neural networks (CNN) on the Hailo-8L accelerator. The search for CNNs that exhibit good accuracy-latency trade-offs on image classification tasks is conducted using NSGA-II and a single-objective genetic algorithm that imposes a performance constraint. To reduce execution time, we adopt a pretrained supernet, introduce an optimized evolution-training interaction, and develop a latency predictor based on a surrogate model. The framework is primarily intended to construct CNN architectures optimized for Hailo-8L and user-provided applicationspecific datasets. Nevertheless, to facilitate a direct comparison with existing methods, we evaluated it on standard image classification benchmarks, specifically CIFAR-10, CIFAR-100, and ImageNet-100.

Anglický abstrakt

A multi-objective, hardware-aware Neural Architecture Search (NAS) framework is introduced and evaluated for efficient design of convolutional neural networks (CNN) on the Hailo-8L accelerator. The search for CNNs that exhibit good accuracy-latency trade-offs on image classification tasks is conducted using NSGA-II and a single-objective genetic algorithm that imposes a performance constraint. To reduce execution time, we adopt a pretrained supernet, introduce an optimized evolution-training interaction, and develop a latency predictor based on a surrogate model. The framework is primarily intended to construct CNN architectures optimized for Hailo-8L and user-provided applicationspecific datasets. Nevertheless, to facilitate a direct comparison with existing methods, we evaluated it on standard image classification benchmarks, specifically CIFAR-10, CIFAR-100, and ImageNet-100.

Klíčová slova

Neural architecture search, Hardware accelerator, Genetic algorithm, Inference latency, Image classification

Klíčová slova v angličtině

Neural architecture search, Hardware accelerator, Genetic algorithm, Inference latency, Image classification

Autoři

NEPRAŠ, D.; SEKANINA, L.

Vydáno

09.05.2026

Nakladatel

Springer Nature

Místo

CHAM

ISBN

978-3-032-23603-6

Kniha

Applications of Evolutionary Computation, EvoApplications

Periodikum

Lecture Notes in Computer Science

Svazek

16524

Stát

Spolková republika Německo

Strany od

484

Strany do

500

Strany počet

17

BibTex

@inproceedings{BUT212657,
  author="David {Nepraš} and Lukáš {Sekanina}",
  title="Multi-objective Evolutionary Neural Architecture Search for Hailo Accelerators",
  booktitle="Applications of Evolutionary Computation, EvoApplications",
  year="2026",
  journal="Lecture Notes in Computer Science",
  volume="16524",
  pages="484--500",
  publisher="Springer Nature",
  address="CHAM",
  doi="10.1007/978-3-032-23604-3",
  isbn="978-3-032-23603-6",
  issn="0302-9743"
}