Parallel Distributed Processing

Viac o knihe

What makes people smarter than computers? The work described in these two volumes suggests that the answer lies in the massively parallel architecture of the human mind. It is some of the most exciting work in cognitive science, unifying neural and cognitive processes in a highly computational framework, with links to artificial intelligence. Although thought and problem solving have a sequential character when viewed over a time frame of minutes or hours, the authors argue that each step in the sequence is the result of the simultaneous activity of a large number of simple computational elements, each influencing others and being influenced by them. "Parallel Distributed Processing" describes their work in developing a theoretical framework for describing this parallel distributed processing activity and in applying the framework to the development of models of aspects of perception, memory, language, and thought.Volume 1 lays the theoretical foundations of parallel distributed processing. It introduces the approach and the reasons why the authors feel it is a fruitful one, describes several models of basic mechanisms with wide applicability to different problems, and presents a number of specific technical analyses of different aspects of parallel distributed models.