论文信息 - Asymptotic performances of a constructive algorithm

Asymptotic performances of a constructive algorithm

We present a numerical study of a neural tree learning algorithm, the “triolearning≓ strategy. We study the behaviour of the algorithm as a function of the size of the training set. The results show that a limited number of examples can be used to estimate both the network performance and the network complexity that would result from running the algorithm on a large data set.

Florence d'Alché-Buc | Jean-Pierre Nadal

[1] Leo Breiman,et al. Classification and Regression Trees , 1984 .

[2] Jean-Pierre Nadal,et al. Neural trees: a new tool for classification , 1990 .

[3] Lawrence D. Jackel,et al. Learning Curves: Asymptotic Values and Rate of Convergence , 1993, NIPS.

[4] Yann LeCun,et al. Measuring the VC-Dimension of a Learning Machine , 1994, Neural Computation.

[5] Jean-Pierre Nadal,et al. Hybrid trees for supervised learning : towards extraction of decision rulesFlorence d ' Alch , 2007 .

[6] M. Golea,et al. A Growth Algorithm for Neural Network Decision Trees , 1990 .

[7] J. Ross Quinlan,et al. Induction of Decision Trees , 1986, Machine Learning.

[8] Marcus Frean,et al. The Upstart Algorithm: A Method for Constructing and Training Feedforward Neural Networks , 1990, Neural Computation.

[9] Robert A. Jacobs,et al. Hierarchical Mixtures of Experts and the EM Algorithm , 1993, Neural Computation.

[10] Jorma Rissanen,et al. Stochastic Complexity in Statistical Inquiry , 1989, World Scientific Series in Computer Science.

[11] Shun-ichi Amari,et al. Statistical Theory of Learning Curves under Entropic Loss Criterion , 1993, Neural Computation.

[12] Florence d'Alché-Buc,et al. Trio Learning: A New Strategy for Building Hybrid Neural Trees , 1994, Int. J. Neural Syst..