Adaptive regression estimation with multilayer feedforward neural networks

Michael C. Kohler, Adam Krzyżak · Journal of nonparametric statistics · 2005

We prove a general bound on the expected L 2 error of adaptive least squares estimates. By applying it to multilayer feedforward neural network regression function estimates, we are able to obtain fast rates of convergence in special classes of regression functions such as additive functions.

Read the paper · More papers on PaperTik