This paper investigates a new learning model in which the input data is corrupted with noise. We present a general statistical framework to tackle this problem. Based on the stati...
Abstract--A crucial issue in designing learning machines is to select the correct model parameters. When the number of available samples is small, theoretical sample-based generali...
Learning curves for Gaussian process (GP) regression can be strongly affected by a mismatch between the ‘student’ model and the ‘teacher’ (true data generation process), e...
The Noise Sensitivity Signature (NSS), originally introduced by Grossman and Lapedes (1993), was proposed as an alternative to cross validation for selecting network complexity. I...
A large number of variants of the Perceptron algorithm have been proposed and partially evaluated in recent work. One type of algorithm aims for noise tolerance by replacing the l...