TY - GEN

T1 - Neural network ensembles and their application to traffic flow prediction in telecommunications networks

AU - Yao, X.

AU - Fischer, M.

AU - Brown, G.

PY - 2001

Y1 - 2001

N2 - It is well-known that large neural networks with many unshared weights can be very difficult to train. A neural network ensemble consisting of a number of individual neural networks usually performs better than a complex monolithic neural network. One of the motivations behind neural network ensembles is the divide-and-conquer strategy, where a complex problem is decomposed into different components each of which is tackled by an individual neural network. A promising algorithm for training neural network ensembles is the negative correlation learning algorithm which penalizes positive correlations among individual networks by introducing a penalty term in the error function. A penalty coefficient is used to balance the minimization of the error and the minimization of the correlation. It is often very difficult to select an optimal penalty coefficient for a given problem because as yet there is no systematic method available for setting the parameter. This paper first applies negative correlation learning to the traffic flow prediction problem, and then proposes an evolutionary approach to deciding the penalty coefficient automatically in negative correlation learning. Experimental results on the traffic flow prediction problem will be presented.

AB - It is well-known that large neural networks with many unshared weights can be very difficult to train. A neural network ensemble consisting of a number of individual neural networks usually performs better than a complex monolithic neural network. One of the motivations behind neural network ensembles is the divide-and-conquer strategy, where a complex problem is decomposed into different components each of which is tackled by an individual neural network. A promising algorithm for training neural network ensembles is the negative correlation learning algorithm which penalizes positive correlations among individual networks by introducing a penalty term in the error function. A penalty coefficient is used to balance the minimization of the error and the minimization of the correlation. It is often very difficult to select an optimal penalty coefficient for a given problem because as yet there is no systematic method available for setting the parameter. This paper first applies negative correlation learning to the traffic flow prediction problem, and then proposes an evolutionary approach to deciding the penalty coefficient automatically in negative correlation learning. Experimental results on the traffic flow prediction problem will be presented.

UR - http://www.scopus.com/inward/record.url?scp=0034844341&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2001.1016718

DO - 10.1109/IJCNN.2001.1016718

M3 - Contribution to conference proceedings

AN - SCOPUS:0034844341

SN - 0-7803-7044-9

T3 - IEEE Xplore

SP - 693

EP - 698

BT - International Joint Conference on Neural Networks (IJCNN'01)

A2 - Marko, Kenneth

A2 - Werbos, Paul

PB - IEEE

CY - New York

T2 - International Joint Conference on Neural Networks (IJCNN'01)

Y2 - 15 July 2001 through 19 July 2001

ER -