Title :
Fast neural network ensemble learning via negative-correlation data correction
Author :
Chan, Zeke S H ; Kasabov, Nik
Author_Institution :
Knowledge Eng. & Discover Res. Inst., Auckland Univ. of Technol., New Zealand
Abstract :
This letter proposes a new negative correlation (NC) learning method that is both easy to implement and has the advantages that: 1) it requires much lesser communication overhead than the standard NC method and 2) it is applicable to ensembles of heterogenous networks.
Keywords :
distributed algorithms; distributed programming; learning systems; neural nets; communication overhead; distributed computing; fast neural network ensemble learning; heterogenous network ensemble; negative correlation data correction; negative correlation learning method; Assembly; Bandwidth; Communication standards; Computer networks; Concurrent computing; Knowledge engineering; Learning systems; Neural networks; Parallel processing; Training data; Distributed computing; ensemble learning; negative correlation (NC) learning; Algorithms; Computer Simulation; Information Storage and Retrieval; Models, Theoretical; Neural Networks (Computer); Numerical Analysis, Computer-Assisted; Statistics as Topic;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2005.852859
