Methodology to Adapt Neural Network on Constrained Device at Topology level - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Methodology to Adapt Neural Network on Constrained Device at Topology level

Abstract

Artificial Intelligence is now ubiquitous as nearly every application domain has found some use for it. The high computational complexity involved in its deployment has led to strong research activity in optimizing its integration in embedded systems. Research works on efficient implementations of CNNs on resource-constrained devices (eg. CPU, FPGA) largely focus on hardware based optimizations such as pruning, quantization or hardware accelerator. However, most performance improvements leading to efficient solutions in terms of memory, complexity and energy are located at the NN topology level, prior to any implementation step. This paper introduces a methodology called ANN2T (Artificial Neural Network to Target) which adapts a pre-trained deep neural network to a designated device with given optimization constraints. ANN2T leverages its included simplifications and/or transformations to progressively modify the deep neural network layers in order to meet the optimization target. Experiment results obtained on microcontroller device show ANN2T produces valuable trade-offs. It achieved up to 33% MACC and 37% memory footprint reductions with no accuracy loss on ResNet-18 topology over the CIFAR-10 dataset. This fully-automated methodology could be generalized to targets such as CPUs, GPUs or FPGAs.
No file

Dates and versions

hal-04381562 , version 1 (09-01-2024)

Identifiers

Cite

Logan Saint-Germain, Bertrand Le Gal, Fabien Baldacci, Jeremie Crenne, Christophe Jego, et al.. Methodology to Adapt Neural Network on Constrained Device at Topology level. 2022 IEEE Workshop on Signal Processing Systems (SiPS), Nov 2022, Rennes, France. pp.1-6, ⟨10.1109/SiPS55645.2022.9919244⟩. ⟨hal-04381562⟩
10 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More