Convolutional Neural Networks

Quan Zhang

2018

Abstract

The earliest Convolution Neural Network (CNN) model is leNet-5 model proposed by LeCun in 1998. However, in the next few years, the development of CNN had been almost stopped until the article ‘Reducing the dimensionality of data with neural networks’ presented by Hinton in 2006. CNN started entering a period of rapid development. AlexNet won the championship in the image classification contest of ImageNet with the huge superiority of 11% beyond the second place in 2012, and the proposal of DeepFace and DeepID, as two relatively successful models for high-performance face recognition and authentication in 2014, marking the important position of CNN. Convolution Neural Network (CNN) is an efficient recognition algorithm widely used in image recognition and other fields in recent years. That the core features of CNN include local field, shared weights and pooling greatly reducing the parameters, as well as simple structure, make CNN become an academic focus. In this paper, the Convolution Neural Network’s history and structure are summarized. And then several areas of Convolutional Neural Network applications are enumerated. At last, some new insights for the future research of CNN are presented.

Paper Citation

in Harvard Style

Zhang Q. (2018). Convolutional Neural Networks.In 3rd International Conference on Electromechanical Control Technology and Transportation - Volume 1: ICECTT, ISBN 978-989-758-312-4, pages 434-439. DOI: 10.5220/0006972204340439

in Bibtex Style

@conference{icectt18,
author={Quan Zhang},
title={Convolutional Neural Networks},
booktitle={3rd International Conference on Electromechanical Control Technology and Transportation - Volume 1: ICECTT,},
year={2018},
pages={434-439},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006972204340439},
isbn={978-989-758-312-4},
}

in EndNote Style

TY - CONF

JO - 3rd International Conference on Electromechanical Control Technology and Transportation - Volume 1: ICECTT,
TI - Convolutional Neural Networks
SN - 978-989-758-312-4
AU - Zhang Q.
PY - 2018
SP - 434
EP - 439
DO - 10.5220/0006972204340439