Title :
Recurrent auto-associative networks and sequential processing
Author :
Stoianov, Ivelin
Author_Institution :
Dept. Alfa-Inf., Groningen Univ., Netherlands
Abstract :
A novel connectionist architecture that develops static representations of structured sequences is presented. The model is based on simple recurrent networks trained on an auto-association task in a way that guarantees the development of unique static representations. The model can be applied in modeling natural language, cognition, etc
Keywords :
learning (artificial intelligence); neural net architecture; recurrent neural nets; auto-associative networks; connectionist architecture; learning; natural language; recurrent neural networks; sequential processing; static representations; Associative memory; Buildings; Cognition; Grounding; Hierarchical systems; Motion pictures; Natural language processing; Natural languages; Radio access networks; Recurrent neural networks;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.832586
