1997-11-17Z2011-03-11T08:54:05Zhttp://cogprints.org/id/eprint/571This item is in the repository with the URL: http://cogprints.org/id/eprint/5711997-11-17ZHow to Make a Low-Dimensional Representation Suitable for Diverse TasksWe consider training classifiers for multiple tasks as a method for improving generalization and obtaining a better low-dimensional representation. To that end, we introduce a hybrid training methodology for MLP networks; the utility of the hidden-unit representation is assessed by embedding it into a 2D space using multidimensional scaling. The proposed methodology is tested on a highly nonlinear image classification task.Nathan IntratorShimon Edelman