TITLE: Design of Robust Neural Network Classifiers
AUTHORS: Jan Larsen, Lars Nonboe Andersen, Mads Hintz-Madsen and Lars Kai Hansen
connect, Department of Mathematical Modelling, Building 321
Technical University of Denmark, DK-2800 Lyngby, Denmark
This paper addresses a new framework for designing robust neural network
classifiers. The network is optimized using the maximum a posteriori technique,
i.e., the cost function is the sum of the log-likelihood and a regularization
term (prior). In order to perform robust classification, we present a
modified likelihood function which incorporate the
potential risk of outliers in the data. This leads to introduction of a new
parameter, the outlier probability. Designing the neural classifier involves
optimization of network weights as well as outlier probability and
parameters. We suggest to adapt the outlier probability and regularization
parameters by minimizing the error on a validation set, and a simple gradient
descent scheme is derived. In addition, the framework allows for constructing
a simple outlier detector.
Experiments with artificial data demonstrates the potential of
the suggested framework.
In Proceedings of ICASSP'98, Seattle, WA, May 12-15, 1998.