Résumé :
|
Researchers in several fields are exploring computational systems in which interesting global behavior emerges from local interactions among components parts ; an approach called emergent computation . In these systems, interactions among simultaneous computations are exploited to improve efficiency, increase flexibility, or to provide more realistic models of natural phenomena. These 31 essays provide definitions for, and explore the concept of, emergent computations in such areas as artificial networks, adaptive systems, classifier systems, connectionist learning, other learning, and biological networks to determine what properties are required of the supporting architectures that generate them.
|