Paper Title:
The Research of Penalty Functions Based on Neural Networks
  Abstract

The penalty functions are introduced in the negative correlation learning for finding a neural network in an ensemble. It is based on the average output of the ensemble. The idea of penalty function based on the average output is to make each individual network has the different output value to that of the ensemble on the same input. Experiments on a classification task show how the negative correlation learning generates a neural network with penalty functions.

  Info
Periodical
Edited by
Helen Zhang and David Jin
Pages
205-208
DOI
10.4028/www.scientific.net/AMM.63-64.205
Citation
Y. Ding, T. J. Wang, X. Fu, "The Research of Penalty Functions Based on Neural Networks", Applied Mechanics and Materials, Vols. 63-64, pp. 205-208, 2011
Online since
June 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Ming Ying Luo
Abstract:This paper presents a candidate set in the case does not produce only scan through a database to extract the top-k strongly correlated item...
1103
Authors: Han Ding Wang, Tao Zhou, Feng Luo
Chapter 4: Development and Utilization of Biomass Energy
Abstract:Supercritical heat transfer correlations are obtained under the certain experimental conditions.The experimental parameters and its...
2692
Authors: Zong Zuo Yu, Jing Feng Wang
Chapter 1: Advanced Material Engineering and Dynamic Systems
Abstract:This paper introduces arithmetic to calculate correlation of two long sequences by using fast correlation method, and the design method of...
35
Authors: Yu Zhuo Men, Hai Bo Yu, Xin Pan
Chapter 5: Intelligent Production
Abstract:In order to study the main influence factors on urban traffic accident, the grey correlation system macroscopic prediction method was...
531
Authors: Hong Yan Xiang, Hong Ling Shu
Chapter 14: Transportation and Traffic Planning, Operation Organization and Management
Abstract:This paper puts forward an ensemble model based on uncertainty simulation and multiple model combination for short-term traffic flow...
1852