Information Technology Journal1812-56381812-5646Asian Network for Scientific Information10.3923/itj.2008.639.646WangXian-Hui QinZheng HengXing-Chen LiuYu 4200874In this study, we put forward a new method to learn
structure of Product Unit Neutral Network (PUNN). The technique used in
our research is based on Particle Swarm Optimization (PSO) algorithm.
The technique can optimized collocate network structure and weight of
the PUNN at the same time using PSO algorithm through standard data set.
Moreover, the number of Hidden Layer units of PUNN is decided by training
set, not prefixed by the designer`s prior knowledge. Particles encoding
scheme is simple and effective. The design of fitness function considers
not only the mean square error between networks output and desired output,
but also the number of hidden layer units. Therefore, the resulting network
can alleviate the problem of over-fitting. The results of the experiment
indicate that PSPUNN algorithm can achieve rational architecture for PUNN
relying on standard data set and the resulting networks hence obtain strong
generalization abilities.]]>Blake, C.L. and C.J. Merz,19981st Edn.,Clerc, M.,19991999pp: 19511957Durbin, R. and D.E. Rumelhart,19901990Engelbrecht, A.P. and A. Ismail,199925974Fahlman, S.E. and C. Lebiere,19901990pp: 524-532pp: 524-532Fischer, M.M.,20022002pp: 12151220Hornik, K., M. Stinchcombe and H. White,19892359366Ismail, A. and A.P. Engelbrecht,20002000pp: 132137Ismail, A. and A.P. Engelbrecht,20022002pp: 257262Janson, D.J. and J.F. Frenzel,199382633Kennedy, J. and R. Eberhart,19951995pp: 19421948Kennedy, J. and R. Eberhart,1997541044108Leerink, L.R., C.L. Giles, B.G. Horne and M.A. Jabri,19957537544Martinez-Estudillo, F.J. and C. Hervas-Martinez,2006422413201328Schmitt, M.,200121253258Shi, Y. and R. Eberhart,19981998pp: 6973Van den Bergh, F. and A.P. Engelbrecht,20011126131