Network with Sub-networks: Layer-wise Detachable Neural Network

DOI

10.2991/jrnal.k.201215.006How to use a DOI?

Keywords

Model compression; neural networks; multilayer perceptron; supervised learning

Abstract

In this paper, we introduce a network with sub-networks: a neural network whose layers can be detached into sub-neural networks during the inference phase. To develop trainable parameters that can be inserted into both base-model and sub-models, first, the parameters of sub-models are duplicated in the base-model. Each model is separately forward-propagated, and all models are grouped into pairs. Gradients from selected pairs of networks are averaged and used to update both networks. With the Modified National Institute of Standards and Technology (MNIST) and Fashion-MNIST datasets, our base-model achieves identical test-accuracy to that of regularly trained models. However, the sub-models result in lower test-accuracy. Nevertheless, the sub-models serve as alternative approaches with fewer parameters than those of regular models.

Copyright

© 2020 The Authors. Published by Atlantis Press B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Ninnart Fuengfusin
AU  - Hakaru Tamukoh
PY  - 2020
DA  - 2020/12/21
TI  - Network with Sub-networks: Layer-wise Detachable Neural Network
JO  - Journal of Robotics, Networking and Artificial Life
SP  - 240
EP  - 244
VL  - 7
IS  - 4
SN  - 2352-6386
UR  - https://doi.org/10.2991/jrnal.k.201215.006
DO  - 10.2991/jrnal.k.201215.006
ID  - Fuengfusin2020
ER  -