Learning of spatiotemporal behaviour in cellular neural networks

International Journal of Circuit Theory and Applications

Volumn 34, Issue 1, 2006, Pages 127-140

  Xavier de Souza, Samuel ^a   Suykens, Johan A K ^a   Vandewalle, Joos ^a  

^a UNIVERSITY OF LEUVEN   (Belgium)

Author keywords

Autowaves; Cellular neural networks; Spatiotemporal behaviour; Trajectory learning

Indexed keywords

COMPUTER SIMULATION; LEARNING SYSTEMS; OPTIMIZATION; PARAMETER ESTIMATION; PROBLEM SOLVING;

AUTOWAVES; SPATIOTEMPORAL BEHAVIOUR; TRAJECTORY LEARNING;

NEURAL NETWORKS;

EID: 32344439375     PISSN: 00989886     EISSN: None     Source Type: Journal    
DOI: 10.1002/cta.346     Document Type: Article

References (28)

1. Shi B, Arena P, Zarándy A (eds). IEEE Transactions on Circuits and Systems-I (Special Issue on CNN Technology and Active Wave Computing) 2004; 51(5):849-1035.
2. Roska T. Computational and computer complexity of analogic cellular wave computers. Journal of Circuits, Systems, and Computers 2003; 12(4):539-556.
3. Földesy P, Kék L, Zarándy A, Bártfai G, Roska T. Fault-tolerant design of analogic CNN templates and algorithms - Part I: the binary output case. IEEE Transactions on Circuits and Systems-I 1999; 46(2): 312-322.
4. Xavier-de-Souza S, Yalcin ME, Suykens JAK, Vandewalle J. Toward CNN chip-specific robustness. IEEE Transactions on Circuits and Systems-I 2004;51(5):892-902.
5. Werbos P. Backpropagation through time: what it does and how to do it. Proceedings of the IEEE 1990; 78(10):1550-1560.
6. Narendra KS, Parthasarathy K. Gradient methods for the optimization of dynamical systems containing neural networks. IEEE Transactions on Neural Networks 1991; 2(2):252-262.
7. Galicki M, Leistritz L, Zwick EB, Witte H. Improving generalization capabilities of dynamic neural networks. Neural Computation 2004; 16(6): 1253-1282.
8. Zegers P, Sundareshan MK. Trajectory generation and modulation using dynamic neural networks. IEEE Transactions on Neural Networks 2003; 14(3):520-533.
9. Bianchini M, Gori M, Maggini M. On the problem of local minima in recurrent neural networks. IEEE Transactions on Neural Networks 1994; 5(2):167-172.
10. Bengio Y, Simard P, Frasconi P. Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks 1994; 5(2):157-166.
11. Cohen B, Saad D, Marom E. Efficient training of recurrent neural network with time delays. Neural Networks 1997; 10(1):51-59.
12. Angeline PJ, Saunders GM, Pollack JB. An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks 1994; 5(1):54-65.
13. Sundareshan MK, Condarcure TA. Recurrent neural-network training by a learning automaton approach for trajectory learning and control system design. IEEE Transactions on Neural Networks 1998; 9(3):354-368.
14. Galicki M, Leistritz L, Witte H. Learning continuous trajectories in recurrent neural networks with time-dependent weights. IEEE Transactions on Neural Networks 1999; 10(4):741-756.
15. Leistritz L, Galicki M, Witte H, Kochs E. Training trajectories by continuous recurrent multilayer networks. IEEE Transactions on Neural Networks 2002; 13(2):283-291.
16. Pearlmutter BA. Gradient calculations for dynamic recurrent neural networks - a survey. IEEE Transactions on Neural Networks 1995; 6(5): 1212-1228.
17. Arena P, Baglio S, Fortuna L, Manganaro G. Self-organization in a two-layer CNN. IEEE Transactions on Circuits and Systems-I 1998; 45(2):157-162.
18. Carmona-Galan R, Jimenez-Garrido F, Dominguez-Mata CM, Dominguez-Castro R, Meana SE, Petras I, Rodriguez-Vazquez A. Second-order neural core for bioinspired focal-plane dynamic image processing in cmos. IEEE Transactions on Circuits and Systems-I 2004; 51(5):913-925.
19. Chua LO, Roska T, Kozek T, Zardy A. CNN Universal chips crank up computing power. IEEE Circuits and Devices 1996; 12(4): 18-28.
20. Xavier-de-Souza S, Suykens JAK, Vandewalle J. Real-time tracking algorithm with locking on a given object for VLSI CNN-UM implementations. Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications, Budapest, Hungary, 2004; 291-296.
21. Pérez-Muñuzuri V, Pérez-Villar V, Chua LO. Autowaves for image processing on a two-dimensional cnn array of excitable nonlinear circuits: flat and wrinkled labyrinths. IEEE Transactions on Circuits and Systems-I 1993; 40(3): 174-181.
22. Adamatzky A, Arena P, Basile A, Carmona-Galan R, Costello BDL, Fortuna L, Frasca M, Rodriguez-Vazquez A. Reaction-diffusion navigation robot control: from chemical to VLSI analogic processors. IEEE Transactions on Circuits and Systems-I 2004; 51(5):926-938.
23. Munuzuri AP, Perez-Munuzuri V, Gomez-Gesteira M, Chua LO, Perez-Villar V. Spatiotemporal structures in discretely-coupled arrays of non-linear circuits: a review. International Journal of Bifurcation and Chaos in Applied Sciences and Engineering 1995; 5(1):17-50.
24. Roska T, Chua LO, Wolf D, Kozek T, Tetzlaff R, Puffer F. Simulating nonlinear waves and partial differential equations via CNN - Part I: basic techniques. IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications 1995; 42(10):807-815.
25. Yalcin ME, Suykens JAK. Spatiotemporal pattern formation on the ACE16k CNN chip. International Journal of Bifurcation and Chaos, 2006 (in press).
26. Rodríguez-Vázquez A, Liñán Cembrano G, Carranza L, Roca-Moreno E, Carmona-Gálan R, Jiménez-Garrido F, Domínguez-Castro R, Meana SE. ACE16k: the third generation of mixed-signal SIMD-CNN ACE chips toward VSoCs. IEEE Transactions on Circuits and Systems-I 2004; 51(5):851-863.
27. Ingber L. Adaptive simulated annealing (ASA): lessons learned. Journal of Control and Cybernetics 1996; 25(1):33-54.
28. Liñán G, Espejo S, Domínguez-Castro R, Rodríguez-Vázquez A. ACE4k: an analog I/O 64 x 64 visual microprocessor chip with 7-bit analog accuracy. International Journal of Circuit Theory and Applications 2002; 30(2-3):89-116.