Hill climbing in recurrent neural networks for learning the an/bsup n/cn language

ICONIP 1999, 6th International Conference on Neural Information Processing - Proceedings

Volumn 2, Issue , 1999, Pages 508-513

  Chalup, Stephau ^a   Blair, Alan D ^b,c  

^a QUEENSLAND UNIVERSITY OF TECHNOLOGY   (Australia)

^b UNIVERSITY OF QUEENSLAND   (Australia)

^c UNIVERSITY OF MELBOURNE   (Australia)

Author keywords

[No Author keywords available]

Indexed keywords

CONTEXT SENSITIVE LANGUAGES;

3D GRAPHS; CONTEXT SENSITIVE; HIDDEN UNITS; HILL CLIMBING; INCREMENTAL LEARNING; PREDICTION TASKS; SIMPLE RECURRENT NEURAL NETWORKS; SYMBOL SEQUENCES;

RECURRENT NEURAL NETWORKS;

EID: 0002684367     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICONIP.1999.845646     Document Type: Conference Paper

References (15)

1. Casey, M. The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction, Neural Computation 8(6), 1135-1178, 1996.
2. Chalup, S., F. Maire. A study on hill climbing algorithms for neural network training, Proceedings of the Congress on Evolutionary Computation (CEC'99), Washington D.C., 2014-2021, 1999.
3. Elman, J.L. Finding structure in time, Cognitive. Science 14, 179-211, 1990.
4. Elman, J.L. Learning and development in neural networks: The importance of starting small, Cognition 48, 71-99, 1993.
5. Finn, G.D. A recurrent neural network for the language anbn: Fjncoding and decoding binary strings in a neuron's activation function, Internal Report, Machine Learning Research Centre, Queensland University of Technology, 1998.
6. Giles, C.L., C.B. Miller, D. Chen, H.H. Chen, G.Z. Sun, Y.C. Lee. Learning and extracting finite state automata with second-order recurrent neural networks, Neural Computation 4(3), 393-405, 1992.
7. Hoelklobler, S, Y. Kalinke, H, Lehmann. Designing a counter: Another case study of dynamics and activation landscapes in recurrent networks, Proceedings of 21st German Conference on Artificial Intelligence, LNAI 1301, Springer Verlag, 313-324, 1997.
8. Maass, W., P. Orponen. On the effect of analog noise in discrete-time analog computation, Proceedings Neural Information Processing Systems, 218-224, 1996.
9. Pollack, J. The induction of dynamical recognizers, Machine Learning 7, 227-252, 1991.
10. Rodriguez, P., J. Wiles, J.L. Flman. A recurrent neural network that learns to count, Connection Science 11(1), 5-40, 1999.
11. Itumelhart, D.E., G.E. Hinton & R.J. Williams. Learning representations by back-propagating errors, Nature 323, 533-536, 1986.
12. Siegelmann, H.T., E.D. Sontag. Neural networks with real weights: Analog computational complexity, Report SYCON-92-95, 1992.
13. Steijvers, M., P. Grunwald. A recurrent network that performs a context-sensitive prediction task, Proceedings of the 18th Annual Conference of the Cognitive Science Society, Morgan Kauffman, 335-339, 1996.
14. Tonkes, B., A. Blair, J. Wiles. Inductive bias in context-free language learning, Proceedings of the Ninth Australian Conference on Neural Networks (ACNN'98), Brisbane, 52-56, 1998.
15. Wiles, J., J. Elman. Learning to count without a counter: A case study of dynamics and activation landscapes in recurrent neural networks, Proceedings of the Seventeenth Annual Conference of the Cognitive Science Society, 482-487, 1995.