Convergence of BP Algorithm for Training MLP with Linear Output

(整期优先)网络出版时间:2007-03-13
/ 1
Thecapabilityofmultilayerperceptrons(MLPs)forapproximatingcontinuousfunctionswitharbitraryaccuracyhasbeendemonstratedinthepastdecades.Backpropagation(BP)algorithmisthemostpopularlearningalgorithmfortrainingofMLPs.Inthispaper,asimpleiterationformulaisusedtoselecttheleamingrateforeachcycleoftrainingprocedure,andaconvergenceresultispresentedfortheBPalgo-rithmfortrainingMLPwithahiddenlayerandalinearoutputunit.Themonotonicityoftheerrorfunctionisalsoguaranteedduringthetrainingiteration.