DocumentCode :
1637781
Title :
Genetic cascade learning for neural networks
Author :
Karunanithi, Nachimuthu ; Das, Rajarshi ; Whitley, Darrell
Author_Institution :
Dept. of Comput. Sci., Colorado State Univ., Fort Collins, CO, USA
fYear :
1992
fDate :
6/6/1992 12:00:00 AM
Firstpage :
134
Lastpage :
145
Abstract :
Genetic cascade learning is a new constructive algorithm for connectionist learning which combines genetic algorithms and the architectural feature of the cascade-correlation learning algorithm. Like the cascade-correlation learning architecture, this new algorithm also starts with a minimal network and dynamically builds a suitable cascade structure by training and installing one hidden unit at a time until the problem is successfully learned. This step-wise constructive algorithm exhibits more scalability than existing genetic algorithms and is free of the competing conventions problem which results from the fact that functionally equivalent networks may have different assignments of functionality to individual hidden units. Initial tests of genetic cascade learning are carried out on a difficult supervised learning problem as well as a reinforcement learning control problem
Keywords :
genetic algorithms; learning (artificial intelligence); neural nets; cascade-correlation learning algorithm; connectionist learning; genetic cascade learning; neural networks; reinforcement learning control problem; scalability; step-wise constructive algorithm; supervised learning; Computer science; Electronic mail; Encoding; Genetic algorithms; Network topology; Neural networks; Scalability; Size control; Supervised learning; Testing;
fLanguage :
English
Publisher :
ieee
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
Type :
conf
DOI :
10.1109/COGANN.1992.273942
Filename :
273942
Link To Document :
بازگشت