Learning multidimensional signal processing

TL;DR: This paper presents the general strategy for designing learning machines as well as a number of particular designs based on two main principles: simple adaptive local models; and adaptive model distribution.

Abstract: This paper presents our general strategy for designing learning machines as well as a number of particular designs. The search for methods allowing a sufficient level of adaptivity are based on two main principles: 1) simple adaptive local models; and 2) adaptive model distribution. Particularly important concepts in our work is mutual information and canonical correlation. Examples are given on learning feature descriptors, modeling disparity, synthesis of a global 3-mode model and a setup for reinforcement learning of online video coder parameter control.