How Bad May Learning Curves Be?
IEEE Transactions on Pattern Analysis and Machine Intelligence
Model abstraction for discrete event systems using neural networks and sensitivity information
Proceedings of the 32nd conference on Winter simulation
Exponential or Polynomial Learning Curves? Case-Based Studies
Neural Computation
| Hi-index | 0.00 |
A tight bound on the generalization performance of concept learning is shown by a novel approach. Unlike existing theories, the new approach uses no assumption on large sample size as in Bayesian approach and does not consider the uniform learnability as in the VC dimension analysis. We analyze the generalization performance of some particular learning algorithm that is not necessarily well behaved, in the hope that once learning curves or sample complexity of this algorithm is obtained, it is applicable to real learning situations. The result is expressed in a dimension called Boolean interpolation dimension, and is tight in the sense that it meets the lower bound requirement of Baum and Haussler (1989). The Boolean interpolation dimension is not greater than the number of modifiable system parameters, and definable for almost all the real-world networks such as backpropagation networks and linear threshold multilayer networks. It is shown that the generalization error follows from a beta distribution of parameters m, the number of training examples, and d, the Boolean interpolation dimension. This implies that for large d, the learning results tend to the average-case result, known as the self-averaging property of the learning. The bound is shown to be applicable to the practical learning algorithms that can be modeled by the Gibbs algorithm with a uniform prior. The result is also extended to the case of inconsistent learning