1. First- and second-order methods for learning: between steepest descent and Newton's method;Battiti;Neural Comput.,1992
2. Introduction to the Theory of Neural Computation;Hertz,1991
3. A method to directly estimate the number of the hidden neurons in the feedforward neural networks;Li;J. Comput.,1999
4. Lin, G., 1991. Using multi-variable analysis method to evaluate the quality of Chinese tea and Japanese tea. Doctoral thesis of MingCheng University (in Japanese).
5. A neural network construction algorithm which maximizes the likelihood function;Setiono;Connect. Sci.,1995