Title :
Regular language inference using evolving neural networks
Author :
Lindgren, Kristian ; Nilsson, A. ; Nordahl, Mats G. ; Råde, Ingrid
Author_Institution :
Inst. of Phys. Resource Theory, Chalmers Univ. of Technol., Goteborg, Sweden
fDate :
6/6/1992 12:00:00 AM
Abstract :
Regular language inference is studied using evolving recurrent neural networks that may change in size through mutations. The scaling of the learning time when information theoretic properties of the test problems are varied is also investigated
Keywords :
finite automata; formal languages; inference mechanisms; information theory; learning (artificial intelligence); recurrent neural nets; evolving neural networks; finite automata; formal languages; information theoretic properties; learning time; regular language inference; Algorithm design and analysis; Automata; Genetic algorithms; Genetic mutations; Heuristic algorithms; Inference algorithms; Neural networks; Recurrent neural networks; Statistical distributions; System testing;
Conference_Titel :
Combinations of Genetic Algorithms and Neural Networks, 1992., COGANN-92. International Workshop on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-8186-2787-5
DOI :
10.1109/COGANN.1992.273947
