Premium
Support vector machine based training of multilayer feedforward neural networks as optimized by particle swarm algorithm: Application in QSAR studies of bioactivity of organic compounds
Author(s) -
Lin WeiQi,
Jiang JianHui,
Zhou YanPing,
Wu HaiLong,
Shen GuoLi,
Yu RuQin
Publication year - 2006
Publication title -
journal of computational chemistry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.907
H-Index - 188
eISSN - 1096-987X
pISSN - 0192-8651
DOI - 10.1002/jcc.20561
Subject(s) - overfitting , artificial neural network , support vector machine , particle swarm optimization , computer science , backpropagation , quantitative structure–activity relationship , convergence (economics) , artificial intelligence , feedforward neural network , local optimum , algorithm , machine learning , mathematical optimization , mathematics , economics , economic growth
Multilayer feedforward neural networks (MLFNNs) are important modeling techniques widely used in QSAR studies for their ability to represent nonlinear relationships between descriptors and activity. However, the problems of overfitting and premature convergence to local optima still pose great challenges in the practice of MLFNNs. To circumvent these problems, a support vector machine (SVM) based training algorithm for MLFNNs has been developed with the incorporation of particle swarm optimization (PSO). The introduction of the SVM based training mechanism imparts the developed algorithm with inherent capacity for combating the overfitting problem. Moreover, with the implementation of PSO for searching the optimal network weights, the SVM based learning algorithm shows relatively high efficiency in converging to the optima. The proposed algorithm has been evaluated using the Hansch data set. Application to QSAR studies of the activity of COX‐2 inhibitors is also demonstrated. The results reveal that this technique provides superior performance to backpropagation (BP) and PSO training neural networks. © 2006 Wiley Periodicals, Inc. J Comput Chem 28: 519–527, 2007