论文信息 - A soft-competitive splitting rule for adaptive tree-structured neural networks

A soft-competitive splitting rule for adaptive tree-structured neural networks

An algorithm for generating tree structured neural networks using a soft-competitive recursive partitioning rule is described. It is demonstrated that this algorithm grows robust, honest estimators. Preliminary results on a 10-class, 240-dimensional optical character recognition classification task show that the tree outperforms backpropagation. Arguments are made that suggest why this should be the case. The connection of the soft-competitive splitting rule to the twoing rule is described.<<ETX>>

M. P. Perrone | M. Perrone

[1] William H. Press,et al. Numerical recipes , 1990 .

[2] M. P. Perrone. A novel recursive partitioning criterion , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[3] R. Mammone,et al. Neural tree networks , 1992 .

[4] William H. Press,et al. Numerical Recipes in FORTRAN - The Art of Scientific Computing, 2nd Edition , 1987 .

[5] Geoffrey E. Hinton,et al. The Bootstrap Widrow-Hoff Rule as a Cluster-Formation Algorithm , 1990, Neural Computation.

[6] Terence D. Sanger,et al. A Tree-Structured Algorithm for Reducing Computation in Networks with Separable Basis Functions , 1991, Neural Computation.

[7] Geoffrey E. Hinton,et al. Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[8] W. Press,et al. Numerical Recipes: The Art of Scientific Computing , 1987 .