INVARIANCE AND NEURAL NETS

Invariance with respect to certain transformations is one of the main tasks of pattern-recognition systems. We study various techniques for obtaining this invariance with neural net classifiers and identify the invariant-feature technique as the most suitable for current neural classifiers. A new formulation of invariance in terms of constraints on the feature values leads to a general method for transforming any given feature space so that it becomes invariant to specified transformations. A case study using range imagery is used to exemplify these ideas, and good performance is obtained.