Hysteretic Hopfield network with dynamic tunneling for crossbar switch and N-queens problem

Neurocomputing

Volumn 70, Issue 13-15, 2007, Pages 2544-2551

  Thangavel, P ^a   Gladis, D ^a  

^a UNIVERSITY OF MADRAS   (India)

Author keywords

Crossbar switch problem; Dynamic tunneling; Gradient descent; Hopfield network; Hysteresis; N queens problem

Indexed keywords

COMPUTATIONAL COMPLEXITY; CONVERGENCE OF NUMERICAL METHODS; CROSSBAR EQUIPMENT; HOPFIELD NEURAL NETWORKS; HYSTERESIS;

CROSSBAR SWITCH PROBLEM; DYNAMIC TUNNELING; GRADIENT DESCENT; N-QUEENS PROBLEM;

TELEPHONE SYSTEMS;

ARTICLE; CONTROLLED STUDY; HOPFIELD NEURAL NETWORK; HYSTERESIS; MATHEMATICAL MODEL; NERVE CELL NETWORK; NETWORK LEARNING; PRIORITY JOURNAL; PROBLEM SOLVING; TRAINING;

EID: 34249739672     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2006.06.006     Document Type: Article

References (14)

1. Bharitkar S., and Mendel J.M. The hysteretic Hopfield neural network. IEEE Trans. Neural Networks 11 4 (2000) 879-888
2. Hopfield J.J. Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. 79 (1982) 2554-2558
3. Hopfield J.J. Neurons with graded response have collective computational properties like those of two state neurons. Proc. Natl. Acad. Sci. 812 (1984) 3088-3092
4. Mandziuk J. A neural network designed to solve the N-queens problem. Biol. Cybern. 66 4 (1992) 375-379
5. Nakaguchi T., Jinno K., and Tanaka M. Hysteresis neural networks for N-queens problem. IEICE Trans. Fundam. 82-A 9 (1999) 1851-1859
6. RoyChowdhury P., Singh Y.P., and Chansarkar R.A. Hybridization of gradient descent algorithms with dynamic tunneling methods for global optimization. IEEE Trans. Syst. Man Cybern.-Part A 30 3 (2000) 384-390
7. Smith K.A. Neural networks for combinatorial optimization: a review of more than a decade of research. INFORMS J. Comput. 11 1 (1999) 15-30
8. Takefuji Y., and Lee K.C. An hysteresis binary neuron: a model suppressing the oscillatory behaviour of neural dynamics. Biol. Cybern. 64 5 (1991) 353-356
9. Thangavel P., and Kathirvalavakumar T. Training feedforward network using simultaneous perturbation with dynamic tunneling. Neurocomputing 48 (2002) 691-704
10. Troudet T.P., and Walters S.M. Neural network architecture for crossbar switch control. IEEE Trans. Circuits Syst. 38 1 (1991) 42-56
11. Wang L.P. Suppressing chaos with hysteresis in a higher order neural network. IEEE Trans. Circuits Syst.-II 43 12 (1996) 845-846
12. Wang L.P., and Ross J. Synchronous neural networks of nonlinear threshold elements with hysteresis. Proc. Natl. Acad. Sci. (USA) 87 (1990) 988-992
13. Xia G., Tang Z., Li Y., and Wang J. A binary Hopfield neural network with hysteresis for large crossbar packet-switches. Neurocomputing 67 (2005) 417-425
14. Yao Y. Dynamic tunneling algorithm for global optimization. IEEE Trans. Syst. Man Cybern. 19 5 (1989) 1222-1230