Kernel-Based Learning from Infinite Dimensional 2-Way Tensors

Abstract. In this paper we elaborate on a kernel extension to tensorbased data analysis. The proposed ideas find applications in supervised learning problems where input data have a natural 2-way representation, such as images or multivariate time series. Our approach aims at relaxing linearity of standard tensor-based analysis while still exploiting the structural information embodied in the input data.

• Type: Conference
• Year: 2010
• Where: ICANN
• Authors: Marco Signoretto, Lieven De Lathauwer, Johan A. K. Suykens
• Keywords: ICANN 2010, Input Data, Neural Networks, Supervised Learning Problems, Tensorbased Data Analysis