Image Recognition based on Dynamic Highway Networks [基於動態高速公路類神經網路之圖像識別研究]
Journal
Journal of the Chinese Society of Mechanical Engineers, Transactions of the Chinese Institute of Engineers, Series C/Chung-Kuo Chi Hsueh Kung Ch'eng Hsuebo Pao
Journal Volume
42
Journal Issue
1
Pages
23-31
Date Issued
2021
Author(s)
Abstract
With the development of machine learning technology, more and more complex networks are developed. For those networks, determining the hyperparameters is important so that they can provide the best performance under the structure of neural network. However, more parameters should be decided in complex networks. This paper is focused on developing a structure of neural networks which can tune the width in each layer based on the utility of neurons automatically. In order to realize this function, a new structure of neural network called convolution neural network based dynamic highway network is proposed to deal with image recognition problem. With the self-adjusting method, near optimal structure and few parameters are required for training to achieve the same and even better performance which uses more neurons. ? 2021, Chinese Mechanical Engineering Society. All right reserved.
Subjects
Dynamic highway networks
Highway networks
Machine learning
Complex networks
Image recognition
Motor transportation
Structural optimization
Convolution neural network
Hyperparameters
Machine learning technology
Near-optimal
ON dynamics
Self-adjusting
Multilayer neural networks
Type
journal article