Training spatially homogeneous fully recurrent neural networks in eigenvalue space

Neural Networks

Volumn 10, Issue 1, 1997, Pages 125-137

  Perfetti, Renzo ^a   Massarelli, Emanuele ^b  

^a UNIVERSITY OF PERUGIA   (Italy)

^b SAPIENZA UNIVERSITY OF ROME   (Italy)

Author keywords

discrete Fourier transform; eigenvalue space; feature extraction; global asymptotic stability; learning algorithm; recurrent neural networks; spatial homogeneity

Indexed keywords

ADAPTATION; DISCRETE FOURIER TRANSFORMS; EIGENVALUE SPACE; GLOBAL ASYMPTOTIC STABILITY; RECURRENT NEURAL NETWORKS; SPATIAL HOMOGENEITY; TRAINING ALGORITHMS;

ASYMPTOTIC STABILITY; COMPUTER SIMULATION; EIGENVALUES AND EIGENFUNCTIONS; FEATURE EXTRACTION; FOURIER TRANSFORMS; LEARNING ALGORITHMS;

NEURAL NETWORKS;

ADAPTATION; ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; LEARNING; PRIORITY JOURNAL;

EID: 0031028913     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(96)00079-2     Document Type: Article

References (18)

1. Almeida, L. B. (1989). Backpropagation in non-feedforward networks. In I. Alexander (Ed.), Neural computing architectures (pp. 74-91). London: North Oxford Academic.
2. Barhen, J., Toomarian, N., & Gulati, S. (1990). Adjoint-operator algorithms for learning in neural networks. Proc. of International Joint Conference on Neural Networks, IJCNN-90. IEEE, New York (Vol. I, 512-516).
3. Bhaya, A., Kaszkurewicz, E., & Kozyakin, V. S. (1994). Existence and stability of a unique equilibrium in continuous-valued discrete-time asynchronous Hopfield neural networks. Techn. Rep. BKK94/EE/01, Dept. of Electrical Eng., Fed. Univ. of Rio de Janeiro.
4. Chua, L. O., & Yang, L. (1988). Cellular neural networks: theory and applications. IEEE Trans. on Circuits and Systems, CAS-35, 1257-1290.
5. Davis, P. J. (1979). Circulant Matrices, New York, Wiley.
6. Dudgeon, D. E., & Mersereau, R. M. (1984). Multidimensional Digital Signal Processing, New Jersey: Prentice-Hall.
7. Gonzalez, R. C., & Wintz, P. (1987). Digital Image Processing. Menlo Park, CA: Addison-Wesley.
8. Hirsch, M. W. (1989). Convergent activation dynamics in continuous time neural networks. Neural Networks, 2, 331-349.
9. Jin, L., Nikiforuk, P. N., & Gupta, M. M. (1994). Absolute stability conditions for discrete-time recurrent neural networks. IEEE Transactions on Neural Networks, 5, 954-964.
10. Karakasoglu, A., Sudharsanan, S. I., & Sundareshan, M. K. (1993). Identification and decentralized adaptive control using dynamical neural networks with application to robotic manipulators. IEEE Transactions on Neural Networks, 4, 919-930.
11. Kaszkurewicz, E., & Bhaya, A. (1993). Robust stability and diagonal liapunov functions. SIAM J. Matrix Analysis Appl., 14, 508-520.
12. Kelly, D. G. (1990). Stability in contractive nonlinear neural networks. IEEE Trans. on Biomedical Engineering, BME-37, 231-242.
13. Krasnoselskii, M., & Zabreiko, P. (1975). Geometrical Methods in Nonlinear Analysis, New York: Springer Verlag.
14. Liu, D., & Michel, A. N. (1994). Sparsely interconnected neural networks for associative memories with applications to cellular neural networks. IEEE Trans. on Circuits & Systems, Part II, CAS-41, 295-307.
15. Marcus, C. M., & Westervelt, R. M. (1989). Dynamics of iterated-map neural networks. Physical Review A, 40, 501-504.
16. Matsuoka, K. (1992a). Absolute stability of neural networks. Systems and Computers in Japan, 23, 102-109.
17. Matsuoka, K. (1992b). Stability conditions for nonlinear continuous neural networks with asymmetric connection weights. Neural Networks, 5, 495-500.
18. Michel, A. N., Farrell, J. A., & Porod, W. (1988). Stability results for neural networks. In D. Z. Anderson (Ed.), Neural Information Processing Systems (pp. 554-563). New York: American Institute of Physics.