Title :
Hill climbing in recurrent neural networks for learning the an bncn language
Author :
Chalup, Stcphau ; Blair, Alan D.
Author_Institution :
Fac. of Inf. Technol., Queensland Univ. of Technol., Brisbane, Qld., Australia
Abstract :
A simple recurrent neural network is trained on a one-step look ahead prediction task for symbol sequences of the context-sensitive a nbncn language. Using an evolutionary hill climbing strategy for incremental learning the network learns to predict sequences of strings up to depth n=12. Experiments and the algorithms used are described. The activation of the hidden units of the trained network is displayed in a 3D graph and analysed
Keywords :
context-sensitive languages; learning (artificial intelligence); recurrent neural nets; sequences; 3D graph; context-sensitive anbncn language learning; evolutionary hill climbing strategy; hidden unit activation; incremental learning; one-step look ahead prediction task; recurrent neural networks; string sequence prediction; symbol sequences; trained network; Australia; Computer networks; Intelligent networks; Neural networks; Recurrent neural networks;
Conference_Titel :
Neural Information Processing, 1999. Proceedings. ICONIP '99. 6th International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-5871-6
DOI :
10.1109/ICONIP.1999.845646
