Abstract—In this paper, an output partitioning algorithm is proposed to improve the performance of neural network (NN) learning. It is assumed that negative interaction among output attributes may lower training accuracy when we have only one single network to produce all the outputs. Our output partitioning algorithm partitions the output space into multiple groups according to correlation, with strong correlation within each group. After partitioning, each group employs a learner to train itself. The training results from each group are integrated to produce the final result. According to our experimental results, the accuracy of NN is improved.
Index Terms—Output attributes, partition, correlation, interference, neural network.
Shang Yang, Sheng-Uei Guan, Shujuan Guo and Hong Xia Xue are with the School of Electronic & Information Engineering, Xi’an Jiaotong University, Xi’an, China (e-mail: Steven.Guan@xjtlu.edu.cn)
Lin Fan Zhao and Wei Fan Li are with the Dept. of Computer Science and Software Engineering, Xi’an Jiaotong-Liverpool University, Suzhou, China.
[PDF]
Cite:Shang Yang, Sheng-Uei Guan, Shu Juan Guo, Lin Fan Zhao, Wei Fan Li, and Hong Xia Xue, "Neural Network Output Partitioning Based on Correlation," Journal of Clean Energy Technologies vol. 1, no. 4, pp. 342-345, 2013.