TITLE: Unsupervised Learning and Generalization AUTHOR: Lars Kai Hansen and Jan Larsen AFFILATION: CONNECT, Section for Digital Signal Processing Department of Mathematical Modelling, B349 Technical University of Denmark\ DK-2800 Lyngby, Denmark Phones: +45 4525+ ext.\ 3889,3923 Fax: +45 45880117 emails: lkhansen,jlarsen@ei.dtu.dk ABSTRACT: The concept of generalization is defined for a general class of unsupervised learning machines. The generalization error is a straightforward extension of the corresponding concept for supervised learning, and may be estimated empirically using a test set or by statistical means -- in close analogy with supervised learning. The empirical and analytical estimates are compared for Principal Component Analysis and for K-means clustering based density estimation. Appears in Proceedings of the IEEE International Conference on Neural Networks, Washington DC, June 1996.