| |
|
A Blueprint of a Conscious Cognitive Agent with Two Internal World Models
Wiedermann, Jiří
We sketch a simple, yet cognitive powerful architecture of a cognitive agent. Our model differs from other similar models by using two complementary internal world models. We know that cognitive potential of one model goes beyond that of the earlier models by its support of algorithmic processes that in their consequences reflect higher cognitive functions such as imitation learning and communication, language, thinking and consciousness development.
|
| |
| |
|
From the Brain in the Vat and Turing Test Towards Humanid Cognitive System
Wiedermann, Jiří
The modern theory of artificial cognitive systems sees these systems as autonomous embodied computational systems that situate themselves in the environment with the help of their sensomotoric units. Still, within the circles of computer theorists one can repeatedly hear an opinion that in principle cognition can be seen as a specific sort of computation and therefore one need not resort to embodiment in order to understand the nature of cognitive processes. We show that such a simplified view misses an essential part of cognitive systems – namely their active influencing the choice or even generation of their inputs.
|
| |
| |
| |
|
Mohou kognitivní a inteligentní systémy překonat Turingovy stroje?
Wiedermann, Jiří
We look for computational limits of artificial, natural and hybrid cognitive and intelligent systems. The common basis for such studies is offered by computationalism, i.e., the belief that cognitive or intelligent processes, respectively, are in essence computational processes. We show that in principle cognitive systems might exist whose computational power outperforms that of Turing machines and that even in practice we observe the rudiments of such systems.
|
|
Unlimited Evolutionary Growth of the Computational Power of Self-Reproducing Automata and Other Results
Wiedermann, Jiří
We design two original computational models - viz. a globular universe and the autopoietic automata - capturing essential features of evolution: the construction of self-reproducing evolutionary automata via self-assembly and genetic information transfer from the parents to their offsprings. Within this framework we show the unlimited growth of the computational power of automata during their evolution and we characterize the power of lineages of such automata with the help of interactive Turing machines.
|