Multi-Complexity-Loss DNAS for Energy-Efficient and Memory-Constrained Deep Neural Networks


METADATA ONLY
Loading...

Date

2022

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Neural Architecture Search (NAS) is increasingly popular to automatically explore the accuracy versus computational complexity trade-off of Deep Learning (DL) architectures. When targeting tiny edge devices, the main challenge for DL deployment is matching the tight memory constraints, hence most NAS algorithms consider model size as the complexity metric. Other methods reduce the energy or latency of DL models by trading off accuracy and number of inference operations. Energy and memory are rarely considered simultaneously, in particular by low-search-cost Differentiable NAS (DNAS) solutions. We overcome this limitation proposing the first DNAS that directly addresses the most realistic scenario from a designer's perspective: the co-optimization of accuracy and energy (or latency) under a memory constraint, determined by the target HW. We do so by combining two complexity-dependent loss functions during training, with independent strength. Testing on three edge-relevant tasks from the MLPerf Tiny benchmark suite, we obtain rich Pareto sets of architectures in the energy vs. accuracy space, with memory footprints constraints spanning from 75% to 6.25% of the baseline networks. When deployed on a commercial edge device, the STM NUCLEO-H743ZI2, our networks span a range of 2.18x in energy consumption and 4.04% in accuracy for the same memory constraint, and reduce energy by up to 2.2 with negligible accuracy drop with respect to the baseline.

Publication status

published

Book title

ISLPED '22: Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design

Journal / series

Volume

Pages / Article No.

28

Publisher

Association for Computing Machinery

Event

Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED '22)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Deep Learning; TinyML; Energy-efficiency; NAS

Organisational unit

03996 - Benini, Luca / Benini, Luca check_circle

Notes

Funding

Related publications and datasets