Design of robust neural network classifiers

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 introductLon of a new parameter, the outlier probability. Designing -.he neural classifier involves optimization of network weights as well as outlier probability and regularization 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 i,he potential of the suggested framework.