Title :
Genetic evolution of neural networks that remember
Author :
Dávila, Jaime J.
Author_Institution :
Sch. of Cognitive Sci., Hampshire Coll., Amherst, MA, USA
fDate :
6/24/1905 12:00:00 AM
Abstract :
The GENDALC system has been previously used to evolve NN topologies for natural language tasks. This paper presents results on additional tasks that require remembering and processing of previous input patterns. These results indicate that GENDALC is particularly well suited for tasks that require remembering
Keywords :
genetic algorithms; network topology; neural nets; software packages; GENDALC; NN topologies; genetic evolution; layer connection; neural network topologies; neuron distribution; Bioinformatics; Cognitive science; Educational institutions; Genetics; Genomics; Natural language processing; Natural languages; Network topology; Neural networks; Neurons;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007656
