A significant problem for evolving artificial neural networks is that the physical arrangement of sensors and effectors is invisible to the evolutionary algorithm. For example,...
This paper presents Fuzzy-UCS, a Michigan-style Learning Fuzzy-Classifier System designed for supervised learning tasks. Fuzzy-UCS combines the generalization capabilities of UCS...
Albert Orriols-Puig, Jorge Casillas, Ester Bernad&...
Embedded systems are often used in a safety-critical context, e.g. in airborne or vehicle systems. Typically, timing constraints must be satisfied so that real-time embedded syste...
The synergy of software and hardware leads to efficient application expression profile (AEP) not only in terms of execution time and energy but also optimal architecture usage. We...
I present MOSES (meta-optimizing semantic evolutionary search), a new probabilistic modeling (estimation of distribution) approach to program evolution. Distributions are not esti...