NEURAI NETWORKS IN Q. S. A. R STUDIES:Estimation and prediction of The anticonvuisant activities of thirty─eight cinnamamides

ltheory1.lprincipleoftheModifiedback-pr0pagation(MBP){'j1.2AIgorithmInthispapper.UsesM.B.PalgorithSupervisedLearn-ing.LeaningSignalC0nsists0ffeed-forwardandbackpropa-gati0n(Fig3).Alqorithm:lISigmoidfunctiony(x)=deIConnectionW',andQ,NInputtraimlngpattenSampleX,.andd:,,ftCalclate(coant)rea1ityValue0foatputY.VregulateWeightW,,W,,(l l)=W,,(l) V8.,01j-outputlayer:6'=y,(lwy,)(d,wy,)v.j-hiddenlayer:3j=O,(l-O,)=3kWjkkkisj(n l)layern0de.bN$O###At4oMBackto4StepContinuediterationuntilerr…

NEURAI NETWORKS IN Q. S. A. R STUDIES:Estimation and prediction of The anticonvuisantactivities of thirty─eight cinnamamides

Neural Networks (NN ) Method was used to study The structure - activity relationship (S. A. R ) of cinnamamide derivatives. The relationship between biological activity (P. C) and thosc parameters such as the Partition coefficients(log p octanol/water) of the compounds Hammett 8 constants and steric parameter(M. R) of cinnamamides were investigated by the modified backpropagation (MBP) Neural Netwoks. The biological activity of cinnamamides derivatives thus estimated and predicted 100% fit with MLP Method. The resalts obtined by the developed MBPNN Method Seem to be better than those by Multivariate linear regression (MLR). The neural Networks Method might therefore be regarded as an excellent and effective chemometric Modelling technique for estim ating and predicting biological cativity on basic Q. S. A. R studies.