RAAM for infinite context-free languages

被引：2
|
作者：
Melnik, O [1 ]
Levy, S [1 ]
Pollack, J [1 ]
机构：
[1] Brandeis Univ, Volen Ctr Complex Syst, Dynam & Evolutionary Machine Org, Waltham, MA 02254 USA
来源：
IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL V | 2000年
关键词：
D O I：
10.1109/IJCNN.2000.861532
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
With its ability to represent variable sized trees in fixed width patterns,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 (a(n)b(n)) but is capable of expressing the whole language.
引用
收藏
页码：585 / 590
页数：6
相关论文
共 50 条
12345