Continuous and discrete deep classifiers for data integration Advances in intelligent data analysis XIV Sokolovska, N. Rizkalla, S. Clément, K. /Zucker, Jean-Daniel Data representation in a lower dimension is needed in applications, where information comes from multiple high dimensional sources. A final compact model has to be interpreted by human experts, and interpretation of a classifier whose weights are discrete is much more straightforward. In this contribution, we propose a novel approach, called Deep Kernel Dimensionality Reduction which is designed for learning layers of new compact data representations simultaneously. We show by experiments on standard and on real large-scale biomedical data sets that the proposed method embeds data in a new compact meaningful representation, and leads to a lower classification error compared to the state-of-the-art methods. We also consider some state-of-the art deep learners and their corresponding discrete classifiers. We illustrate by our experiments that although purely discrete models do not always perform better than real-valued classifiers, the trade-off between the model accuracy and the interpretability is quite reasonable. Springer Fromont, E. (ed.) De Bie, T. (ed.) Van Leeuwen, M. (ed.) 2015 text https://www.documentation.ird.fr/hor/fdi:010072191 fdi:010072191 Sokolovska N., Rizkalla S., Clément K., Zucker Jean-Daniel. Continuous and discrete deep classifiers for data integration. In : Fromont E. (ed.), De Bie T. (ed.), Van Leeuwen M. (ed.), . Advances in intelligent data analysis XIV Springer, ; 9385). 2015, 264-274 IDA : Intelligent Data Analysis 2015, 14., Saint-Etienne (FRA), 2015/10/22-24 EN