Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
Procedural representations of control policies have two advantages when facing the scale-up problem in learning tasks. First they are implicit, with potential for inductive genera...
Self-Modifying Cartesian Genetic Programming (SMCGP) is a form of genetic programming that integrates developmental (self-modifying) features as a genotype-phenotype mapping. This...
Simon Harding, Julian Francis Miller, Wolfgang Ban...
We present a generalization of conventional artificial neural networks that allows for a functional equivalence to multi-expert systems. The new model provides an architectural fr...
—The purpose of this paper is to present a comparison between two methods of building adaptive controllers for robots. In spite of the wide range of techniques which are used for...
Sergiu Goschin, Eduard Franti, Monica Dascalu, San...