See veebileht kasutab küpsiseid kasutaja sessiooni andmete hoidmiseks. Veebilehe kasutamisega nõustute ETISe kasutustingimustega. Loe rohkem
Olen nõus

DeepMaker: A multi-objective optimization framework for deep neural networks in embedded systems

Loni, M.; Sinaei, S.; Zoljodi, A.; Daneshtalab, M.; Sjödin, M. (2020). DeepMaker: A multi-objective optimization framework for deep neural networks in embedded systems. Journal of Functional Foods, 73.10.1016/j.micpro.2020.102989.
ajakirjaartikkel
Loni, M.; Sinaei, S.; Zoljodi, A.; Daneshtalab, M.; Sjödin, M.
  • Inglise
Journal of Functional Foods
0141-9331
73
2020
Ilmunud
1.1. Teadusartiklid, mis on kajastatud Web of Science andmebaasides Science Citation Index Expanded, Social Sciences Citation Index, Arts & Humanities Citation Index, Emerging Sources Citation Index ja/või andmebaasis Scopus (v.a. kogumikud)
Teadmata
SCOPUS

Viited terviktekstile

dx.doi.org/10.1016/j.micpro.2020.102989

Seotud asutused

Shiraz University of Technology; Mälardalens högskola

Lisainfo

© 2020 Deep Neural Networks (DNNs) are compute-intensive learning models with growing applicability in a wide range of domains. Due to their computational complexity, DNNs benefit from implementations that utilize custom hardware accelerators to meet performance and response time as well as classification accuracy constraints. In this paper, we propose DeepMaker framework that aims to automatically design a set of highly robust DNN architectures for embedded devices as the closest processing unit to the sensors. DeepMaker explores and prunes the design space to find improved neural architectures. Our proposed framework takes advantage of a multi-objective evolutionary approach that exploits a pruned design space inspired by a dense architecture. DeepMaker considers the accuracy along with the network size factor as two objectives to build a highly optimized network fitting with limited computational resource budgets while delivers an acceptable accuracy level. In comparison with the best result on the CIFAR-10 dataset, a generated network by DeepMaker presents up to a 26.4x compression rate while loses only 4% accuracy. Besides, DeepMaker maps the generated CNN on the programmable commodity devices, including ARM Processor, High-Performance CPU, GPU, and FPGA.
Convolutional Neural Networks (CNNs) | Design Space Exploration (DSE) | Embedded systems | Multi-Objective Optimization (MOO)