论文信息 - Variable Selection in the Cascade-Correlation Learning Architecture

Variable Selection in the Cascade-Correlation Learning Architecture

Recently there has been a growing interest in the application of neural networks in the field of QSAR. It was demonstrated that this method is often superior to the traditional approaches.1 Other studies have shown that prediction ability of such methods can be substantially improved if the number of input variables for neural networks is optimized.2,3

[1] Igor V. Tetko,et al. Neural Network Studies. 3. Variable Selection in the Cascade-Correlation Learning Architecture , 1998, J. Chem. Inf. Comput. Sci..

[2] Elie Bienenstock,et al. Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[3] Igor V. Tetko,et al. Neural network studies, 1. Comparison of overfitting and overtraining , 1995, J. Chem. Inf. Comput. Sci..

[4] Garrison W. Cottrell,et al. Topology-modifying neural network algorithms , 1998 .

[5] Igor V. Tetko,et al. Neural Network Studies, 2. Variable Selection , 1996, J. Chem. Inf. Comput. Sci..

[6] Desmond J. Maddalena. Review Biologicals & Immunologicals: Applications of artificial neural networks to quantitative structure-activity relationships , 1996 .

[7] Christian Lebiere,et al. The Cascade-Correlation Learning Architecture , 1989, NIPS.

[8] D. Maddalena,et al. Prediction of receptor properties and binding affinity of ligands to benzodiazepine/GABAA receptors using artificial neural networks. , 1995, Journal of medicinal chemistry.