[1] Levin E. Statistical approach to learning and generalization in layered neural networks. Proc. IEEE, 1990,78:1568-1574
[2] Wolpert D H. A mathematical theory of generalization. Part 1, Part Ⅱ. Complex Systems, 1990,4:151-200,201-249
[3] Moody J O. The dependence identification neural network construction algorithm. IEEE Trans. on NN, 1996,7(1):3-15
[4] Amari S. Natural gradiant works efficiently in learning. Neural Computation, 1998,10:251-276