Abstract—This paper presents a new output partitioning approach with the advantages of constructive learning and output parallelism. Classification error is used to guide the partitioning process so that several smaller sub-dimensional data sets are divided from the original data set. When training each sub- dimensional data set in parallel, the smaller constructively trained sub-network uses the whole input vector and produces a portion of the final output vector where each class is represented by one unit. Three classification data sets are used to test the validity of this algorithm, while the results show that this method is feasible.
Index Terms—Constructive learning algorithm, output partitioning, parallel growing, output interference
Shang Yang and Sheng-Uei Guanare are with the School of Electronic & Information Engineering, Xi’an Jiaotong University, Xi’an, China (e-mail: Steven.Guan@xjtlu.edu.cn)
Weifan Li and Linfan Zhao are with the Dept. of Computer Science and Software Engineering, Xi’an Jiaotong-Liverpool University, Suzhou, China
[PDF]
Cite:Shang Yang, Sheng-Uei Guan, Wei Fan Li, and Lin Fan Zhao, "Low-Interference Output Partitioning for Neural Network Training," Journal of Clean Energy Technologies vol. 1, no. 4, pp. 331-334, 2013.
