Selective Fine-Tuning on a Classifier Ensemble: Realizing Adaptive Neural Networks With a Diversified Multi-Exit Architecture

Adaptive neural networks that provide a trade-off between computing costs and inference performance can be a crucial solution for edge artificial intelligence (AI) computing where resource and energy consumption are significantly constrained. Edge AIs require a fine-tuning technique to achieve targe...

Full description

Bibliographic Details
Main Authors: Kazutoshi Hirose, Shinya Takamaeda-Yamazaki, Jaehoon Yu, Masato Motomura
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9309311/