Abstract. Solutions to the symbol grounding problem, in psychologically plausible cognitive models, have been based on hybrid connectionist/symbolic architectures, on robotic appro...
— Traditional approaches to integrating knowledge into neural network are concerned mainly about supervised learning. This paper presents how a family of self-organizing neural m...
We propose a novel, high-level model of human learning and cognition, based on association forming. The model configures any input data stream featuring a high incidence of repeti...
Abstract—Acquisition and representation of semantic concepts is a necessary requirement for the understanding of natural languages by cognitive systems. Word games provide an int...
1 This paper presents a new technique for the design of real-time controllers based on a hybrid approach which integrates several control strategies, such as intelligent controlle...
Marcello Chiaberge, G. Di Bene, S. Di Pascoli, R. ...