Low-Interference Output Partitioning for Neural Network Training

Shang Yang, Sheng-Uei Guan, Wei Fan Li, Lin Fan Zhao
2013 Journal of Clean Energy Technologies  
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
more » ... it. Three classification data sets are used to test the validity of this algorithm, while the results show that this method is feasible.
doi:10.7763/jocet.2013.v1.75 fatcat:oshjfwruwfeqpovtp2fkrvy4q4