Part of Advances in Neural Information Processing Systems 9 (NIPS 1996)
A. Burgess
We describe the notion of "equivalent kernels" and suggest that this provides a framework for comparing different classes of regression models, including neural networks and both parametric and non-parametric statistical techniques. Unfortunately, standard techniques break down when faced with models, such as neural networks, in which there is more than one "layer" of adjustable parameters. We propose an algorithm which overcomes this limitation, estimating the equivalent kernels for neural network models using a data perturbation approach. Experimental results indicate that the networks do not use the maximum possible number of degrees of freedom, that these can be controlled using regularisation techniques and that the equivalent kernels learnt by the network vary both in "size" and in "shape" in different regions of the input space.