Picture Reconstruction Optimization Using Neural Networks

Yiheng Hu, Zhihua Hu, Jin Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The multilayer perceptron (MLP), as one of neural network types, is a function of one or more predictors which minimizes the error between the inputs and target variables. In this paper, the network architecture is designed and the optimal parameters are chosen. A novel method is proposed to add polynomial features to help get better results on the accuracy of reconstruction picture. The number of epochs for training is also an important fact for time consuming which has strong relationship with the avoid overtraining algorithm. The accuracy of the reconstruction work and the size of time consuming data are examined by experimental work.

Original languageEnglish
Title of host publicationRecent Developments in Mechatronics and Intelligent Robotics
Subtitle of host publicationProceedings of the International Conference on Mechatronics and Intelligent Robotics, ICMIR 2017
EditorsFeng Qiao, Srikanta Patnaik, John Wang
PublisherSpringer, Cham
Pages15-20
Number of pages6
Volume690
ISBN (Electronic)9783319659787
ISBN (Print)9783319659770
DOIs
Publication statusPublished - 12 Nov 2017
Externally publishedYes
EventInternational Conference on Mechatronics and Intelligent Robotics - Kunming, China
Duration: 20 May 201721 May 2017

Publication series

NameAdvances in Intelligent Systems and Computing
PublisherSpringer
Volume690
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

ConferenceInternational Conference on Mechatronics and Intelligent Robotics
Abbreviated titleICMIR 2017
Country/TerritoryChina
CityKunming
Period20/05/1721/05/17

Cite this