The following information was submitted:
Transactions: INTERNATIONAL JOURNAL of MATHEMATICAL MODELS AND METHODS IN APPLIED SCIENCES
Transactions ID Number: 20-670
Full Name: Somkid Amornsamankul
Position: Assistant Professor
Age: ON
Sex: Male
Address: Department of Mathematics, Faculty of Science, Mahidol University
Country: THAILAND
Tel: 02-2015339
Tel prefix: 66
Fax: -
E-mail address: scsam@mahidol.ac.th
Other E-mails: scsam9@yahoo.com,pawalai@yahoo.com
Title of the Paper: Neural Network Regression Based on Falsity Input
Authors as they appear in the Paper: Pawalai Kraipeerapun,Somkid Amornsamankul
Email addresses of all the authors: scsam@mahidol.ac.th,pawalai@yahoo.com
Number of paper pages: 8
Abstract: In general, only the truth input is used to train neural network. This paper applies both truth and falsity input, which is the complement of the truth input, to train neural network to solve regression problems. Four neural networks are created. The first two networks are trained using the truth input to predict the truth and falsity outputs based on the truth and falsity targets, respectively. The last two are trained using the falsity input to predict the truth and falsity outputs as well. In order to add more diversity, ensemble of neural networks is applied. Each component in the ensemble contains four types of neural networks created based on our proposed techniques. Aggregation techniques are proposed to provide more accuracy results. Three classical benchmark data sets from the UCI machine learning repository are used in our experiments. These data sets are housing, concrete compressive strength, and computer hardware. It is found that the four proposed net!
works improve the prediction performance when compared to backpropagation neural network and complementary neural networks.
Keywords: Feedforward Backpropagation Neural Network, Ensemble Neural Networks, Complementary Neural Networks, Regression Problems, Truth Neural Network, Falsity Neural Network
EXTENSION of the file: .pdf
Special (Invited) Session: Applying Falsity Input to Neural Networks to Solve Single Output Regression Problems
Organizer of the Session: 653-167
How Did you learn about congress:
IP ADDRESS: 58.8.201.24
