Computational backpropagation algorithms

J Leonard and MA Kramer. Improvement of the backpropagation algorithm for training neural networks. Comput. Chem. Engg., 14(3) 337-341, 1990. 

The second step of training is the error backpropagation algorithm carried on only for the output layer. Since this is a supervised algorithm for one layer only, the training is very rapid, 100-1000 times faster than in the backpropagation multilayer network. This makes the radial basis-function network very attractive. Also, this network can be easily modeled using computers, however, its hardware implementation would be difficult. 

C. Klawun and C. L. Wilkins,/. Chem. Inf. Comput. Sci., 34,984 (1994). A Novel Algorithm for Local Minimum Escape in Backpropagation Neural Networks Application to the Interpretation of Matrix Isolation Infrared Spectra. 

---