Heterogeneity, mobility, complexity and new application domains raise new software reliability issues that cannot be met cost-effectively only with classic software engineering ap...
Temporal segmentation of facial gestures in spontaneous facial behavior recorded in real-world settings is an important, unsolved, and relatively unexplored problem in facial imag...
Fernando De la Torre, Joan Campoy, Zara Ambadar, J...
Flow composition languages permit the construction of longrunning transactions from collections of independent, atomic services. Due to environmental limitations, such transaction...
Reinforcement learning promises a generic method for adapting agents to arbitrary tasks in arbitrary stochastic environments, but applying it to new real-world problems remains di...
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...