CONVERGENCE OF RECURRENT NETWORKS AS CONTRACTION MAPPINGS

Proceedings of the International Joint Conference on Neural Networks

Volumn 3, Issue , 1992, Pages 462-467

  Steck, James Edward ^a  

^a WICHITA STATE UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

MAPPING; RECURRENT NEURAL NETWORKS;

CONDITION; CONTRACTION MAPPINGS; EXTERNAL INPUT; FIXED POINTS; GLOBAL CONVER-GENCE; INPUT VALUES; NETWORK CONNECTION; NEURON ACTIVATION FUNCTION; RECURRENT ARTIFICIAL NEURAL NETWORKS; RECURRENT NETWORKS;

NETWORK ARCHITECTURE;

EID: 84945713312     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/IJCNN.1992.227131     Document Type: Conference Paper

References (6)

1. Hopfield J . J ., Neurons with graded response have collective computational properties like those of two-state neurons, Proc. Nat. Acad. Sci. USA, Bio., 81, pp 3088-3092, 1984.
2. Pineda F . J ., Time Dependent Adaptive neural Networks, Advances in Neural Information Processing Systems 3, Morgan Kaufmann Publishers, San Mateo CA, 1990.
3. Pearlmutter B. A., Learning State Space Trajectories in Recurrent Neural Networks, Proceedings IntemationalJoint Conf. on Neural Networks, 11-365, 1989.
4. Simard P. Y., Ottaway M. B., Ballard D. H., Analysis of Recurrent Backpropagation, Proceedings Cormectionist Models Summer School 1988, pp 103-112.
5. Gamelin T.W., Greene R . E ., Introduction to Topology, Saunder College Publishing, New York NY, 1983, pp 40-41.
6. Goldberg R.R., Methods ofRealAnalysis, John Wiley and Sons, New York NY, 1976, p 203.