Recurrent neural networks can learn to implement symbol-sensitive counting

Advances in Neural Information Processing Systems

Volumn , Issue , 1998, Pages 87-93

  Rodriguez, Paul ^a   Wiles, Janet ^b  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b UNIVERSITY OF QUEENSLAND   (Australia)

Author keywords

[No Author keywords available]

Indexed keywords

ANALOG COMPUTERS; COMPLEX NETWORKS; DYNAMICAL SYSTEMS; RECURRENT NEURAL NETWORKS; SYSTEMS ANALYSIS;

ANALOG COMPUTATION; COMPLEXITY ANALYSIS; CONSTRAST; DISCRETE-TIME DYNAMICAL SYSTEMS; RECURRENT NEURAL NETWORK (RNNS); SELF ORGANIZED SYSTEMS;

CONTEXT FREE LANGUAGES;

EID: 0002098405     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Casey, M. (1996) The Dynamics of Discrete-Time Computation, With Application to Recurrent Neural Networks and Finite State Machine Extraction. Neural Computation, 8.
2. Elman, J.L. (1990) Finding Structure in Time. Cognitive Science, 14, 179-211.
3. Maass, W., Orponen, P. (1997) On the Effect of Analog Noise in Discrete-Time Analog Computations. Proceedings Neural Information Processing Systems, 1996.
4. Moore, C. (1996) Dynamical Recognizers: Real-Time Language Recognition by Analog Computation. Santa Fe InstituteWorking Paper 96-05-023.
5. Pollack, J.B. (1991) The Induction of Dynamical Recognizers. Machine Learning, 7, 227-252.
6. Siegelmann, H.(1993) Foundations of Recurrent Neural Networks. PhD. dissertation, un-published. New Brunswick Rutgers, The State University of New Jersey.
7. Mies, J., Elman, J. (1995) Counting Without a Counter A Case Study in Activation Dynamics. Proceedings of the Seventeenth Annual Conference of the Cognitive Science Society. Hillsdale, NX: Lawrence Erlbaum Associates.