Title :
A neurointelligence: multisignificance images and neurocomputing
Author_Institution :
Inst. for Problems of Comput., Technol. & Inf., Moscow, USSR
Abstract :
Summary form only given, as follows. Neurointelligence is realized by means of material (neuroelectrical and neurochemical) and neuroinformational processes. The development of new types of neurocomputers requires the use of the `gestalt´ representation of the input patterns and a deeper knowledge of the specific functional mechanisms of the brain (for example, the mechanism asymmetry of the brain). Such mechanisms make it possible to realize the understanding of multi significance images. The problems of the formation of the right hemisphere function for `meaning-text-meaning´ processes and the understanding of metaphors were investigated
Keywords :
artificial intelligence; brain models; neural nets; brain; functional mechanisms; input patterns; neurocomputers; neuroinformational processes; neurointelligence; right hemisphere function; Biological neural networks; Convergence; Hardware; Multi-layer neural network; Neural networks; Very large scale integration;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155552
