This paper is mainly concerned with the application of a novel technique of data interpretation to the characterization and classification of measurements of plasma columns in Tokamak reactors for nuclear fusion applications. The proposed method exploits several concepts derived from soft computing theory. In particular, Artifical Neural Networks have been exploited to classify magnetic variabl...

Neural networks are a popular technique for learning the adaptive control of non-linear plants. When applied to the complex control of android robots, however, they suffer from serious limitations such as the moving target problem, i.e. the interference between old and newly learned knowledge. However, in order to achieve lifelong learning, it is important that robots are able to acquire new mo...

1 Paper presented at the Annual PAASE Meeting and Symposium (APAMS 2007), March 15-17, 2007 Book of Abstracts ( ISSN 1908-5907), Proceedings in CD (IISN: 1908-5982) Artifical Neural Networks (ANNs) are powerful computing tools which were inspired by the neural architecture of the human brain. ANNs adapt solutions and are capable of learning the interrelationships among multiple variables by sim...

“¿Las máquinas pueden pensar?”. Esta pregunta se la formuló Alan Turing1, considerado como el padre de computación, ya en año 1950 (Turing, 1950). Al mismo tiempo, un pequeño juego al que acuñó nombre “juego las imitaciones”. El consiste una persona A interactúa con máquina B y C, e intentará adivinar cuál ellos es máquina. no tiene acceso visual ni sonoro a C: sólo puede comunicar través termi...