Performance bounds for single layer threshold networks when tracking a drifting adversary

Neural Networks

Volumn 10, Issue 5, 1997, Pages 897-906

  Tian, Xiaodong ^a   Kuh, Anthony ^a,b  

^a UNIVERSITY OF HAWAII   (United States)

^b University of Hawaii at Manoa   (United States)

Author keywords

Adaptive systems; Generalization error; Neural networks; System identification; Time varying systems; Tracking drift

Indexed keywords

LEAST MEAN SQUARE (LMS) TRACKER; SINGLE LAYER THRESHOLD NETWORKS; TRACKING DRIFT;

ADAPTIVE CONTROL SYSTEMS; COMPUTER SIMULATION; IDENTIFICATION (CONTROL SYSTEMS); LEARNING ALGORITHMS; PROBABILITY; TIME VARYING SYSTEMS;

NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; PRIORITY JOURNAL;

EID: 0031194820     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(96)00118-9     Document Type: Article

References (15)

1. Bhama, S., & Singh, H. (1993). Single layer neural networks for linear system identification using gradient descent technique. IEEE Transactions on Neural Networks, 4 (5), 884-888.
2. Biehl, M., & Schwarze, H. (1993). Learning drifting concepts with neural networks. Journal of Physics, A, 26 (11), 2651-2665.
3. Cho, S., & Mathews, V. (1990). Tracking analysis of the sign algorithm in nonstationary environments.. IEEE Transactions on Acoustics Speech and Signal Processing, 38 (12), 2046-2057.
4. Eweda, E. (1994). Comparison of RLS, LMS, and Sign algorithms for tracking randomly time-varying channels. IEEE Transactions on Signal Processing, 42 (11), 2937-2944.
5. Gibson, G., Siu, S., & Cowan, C. The application of nonlinear structures to the reconstruction of binary signals. IEEE Transactions of Acoustics Speech and Signal Processing, 39(9), 1877-1884.
6. Haykin, S. (1991). Adaptive filter theory. Englewood Cliffs, NJ: Prentice Hall.
7. Helmbold, D., & Long, P. (1994). Tracking drifting concepts by minimizing disagreements. Machine Learning, 14 (1), 27-45.
8. Kuh, A., & Petsche, T. (1996). Performance bounds for learning in a drifting environment, preprint, submitted to IEEE Transactions on Systems, Man, and Cybernetics.
9. Kuh, A. (1997). Comparison of tracking algorithms for single layer threshold networks in the presence of random drift. IEEE Transactions on Signal Processing. 45(3), 640-649.
10. Price, R. (1958). A useful theorem for nonlinear devices having Gaussian inputs. IRE Transactions on Information Theory, 4 (6), 69-72.
11. Rosenblatt, F. (1962). Principles of Neurodynamics. New York: Spartan.
12. Tian, X., & Kuh, A. (1996). Tracking capabilities of single-layer threshold networks when confronted with drift and random noise. Proceedings of the International Symposium on Circuits and Systems, 3, 376-379.
13. Widrow, B., & Hoff, M.E. (1960). Adaptive Switching circuits. WESCON Convention Record, Part IV, 96-104.
14. Widrow, B., McCool, J.M., Larimore, M.G., & Johnson, C.R. Jr. (1976). Stationary and nonstationary learning characteristics of the LMS adaptive filter. IEEE Proceedings, 64 (8), 1151-1562.
15. Yang, X., & Kuh, A. (1994). Partial recurrent time delay neural network channel equalizer. In World Congress on Neural Networks - San Diego, 3, 20-25.