Based on the thermodynamic concept of a reservoir, we investigate a computational model for interaction with unresolved degrees of freedom (a thermal bath). We assume that a finite...
Abstract--Acquisition of new sensorimotor knowledge by imitation is a promising paradigm for robot learning. To be effective, action learning should not be limited to direct replic...
Context-aware computing systems demand an accurate and up-to-date world model which computationally represents the environment they oversee. Systems to date tend to have small-sca...
In this paper, we present the Dynamic Injection Model (DIM) and its variant the Static Injection Model (SIM). DIM is a model that allows any iterative block cipher to accept a var...
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...