DocumentCode :
353366
Title :
RAAM for infinite context-free languages
Author :
Melnik, Ofer ; Levy, Simon ; Pollack, Jordan
Author_Institution :
Volen Center for Complex Syst., Brandeis Univ., Waltham, MA, USA
Volume :
5
fYear :
2000
fDate :
2000
Firstpage :
585
Abstract :
With its ability to represent variable sized trees in fixed width patterns, recursive auto-associative memory (RAAM) is a bridge between connectionist and symbolic systems. In the past, due to limitations in our understanding, its development plateaued. By examining RAAM from a dynamical systems perspective we overcome most of the problems that previously plagued it. In fact, using a dynamical systems analysis we can now prove that not only is RAAM capable of generating parts of a context free language (anbn) but is capable of expressing the whole language
Keywords :
content-addressable storage; context-free languages; dynamical systems analysis; fixed width patterns; infinite context-free languages; recursive auto-associative memory; variable sized trees; Bridges; Computer errors; Encoding; Iterative decoding; Labeling; Logic testing; Neurons; Prototypes; Tree data structures;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
ISSN :
1098-7576
Print_ISBN :
0-7695-0619-4
Type :
conf
DOI :
10.1109/IJCNN.2000.861532
Filename :
861532
Link To Document :
بازگشت