Fixed point method for autonomous on-line neural network training

Neurocomputing

Volumn 74, Issue 17, 2011, Pages 2893-2905

  Wawrzyński, Paweł ^a   Papis, Bartosz ^a  

^a WARSAW UNIVERSITY OF TECHNOLOGY   (Poland)

Author keywords

Autonomous learning; Extended Kalman Filter; On line learning; Step size adaptation

Indexed keywords

APPROXIMATION PROBLEMS; AUTONOMOUS LEARNING; EXPERIMENTAL STUDIES; FIXED POINT METHODS; LEARNING PROCESS; LOSS FUNCTIONS; ON-LINE NEURAL NETWORKS; ONLINE LEARNING; ONLINE TRAINING; STEEPEST DESCENT; STEP-SIZE ADAPTATION; TRAINING EXAMPLE; TRAINING PROCESS;

EXTENDED KALMAN FILTERS; FEEDFORWARD NEURAL NETWORKS; LEARNING SYSTEMS;

E-LEARNING;

ALGORITHM; ANALYTICAL ERROR; ARTICLE; ARTIFICIAL NEURAL NETWORK; EXPERIMENTAL STUDY; FIXED POINT ALGORITHM; LEARNING; MATHEMATICAL MODEL; MEAN SQUARE ERROR; ON LINE NEURAL NETWORK TRAINING; ONLINE SYSTEM; PRIORITY JOURNAL; PROBLEM SOLVING;

EID: 80052930723     PISSN: 09252312     EISSN: 18728286     Source Type: Journal    
DOI: 10.1016/j.neucom.2011.03.029     Document Type: Article

References (22)

1. Iiguni Y., Sakai H., Tokumaru H. A real time learning algorithm for a multilayered neural network based on Extended Kalman Filter. IEEE Transactions on Signal Processing 1992, 45(6):959-966.
2. F.M. Silva, L.B. Almeida, Acceleration techniques for the backpropagation algorithm, in: Neural Networks EURASIP Workshop, Sesim, 1990.
3. Jacobs R.A. Increased rates of convergence through learning rate adaptation. Neural Networks 1988, 1(4):295-308.
4. N.N. Schraudolph, X. Giannakopoulos, Online independent component analysis with local learning rate adaptation, in: Advances in NIPS, vol. 12, 2000, pp. 789-795.
5. Behera L., Kumar S., Patnaik A. On adaptive learning rate that guarantees convergence in feedforward networks. IEEE Transactions on Neural Networks 2006, 17(5):1116-1125.
6. Kathirvalavakumar T., Subavathi S.J. Neighborhood based modified backpropagation algorithm using adaptive learning parameters for training feedforward neural networks. Neurocomputing 2009, 72:3915-3921.
7. Zak M. Terminal attractors in neural networks. Neural Networks 1989, 2:259-274.
8. Yu X., Wang B., Batbayar B., Wang L., Man Z. An improved training algorithm for feedforward neural network learning based on terminal attractors. Journal of Global Optimization 2010, 1-14.
9. Hagan M.T., Mehnaj M. Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks 1994, 5(6):989-993.
10. Charalambous C. Conjugate gradient algorithm for efficient training of artificial neural networks. Circuits, Devices and Systems, IEE Proceedings G 1992, 139:301-310.
11. B.M. Wilamowski, S. Iplikci, O. Kaynak, M.O. Efe, An algorithm for fast convergence in training neural networks, in: International Joint Conference on Neural Networks, vol. 3, 2001, pp. 1778-1782.
12. Toledo A., Pinzolas M., Ibarrola J.J., Lera G. Improvement of the neighborhood based Levenberg-Marquardt algorithm by local adaptation of the learning coefficient. IEEE Transactions on Neural Networks 2005, 16:988-992.
13. Castillo E., Guijarro-Berdinas B., Fontenla-Romero O., Alonso-Betanzos A. A very fast learning method for neural networks based on sensitivity analysis. Journal of Machine Learning Research 2006, 7:1159-1182.
14. Wawrzyński P. Real-time reinforcement learning by sequential actor-critics and experience replay. Neural Networks 2009, 22:1484-1497.
15. Sutton R.S. Adapting bias by gradient descent: an incremental version of delta-bar-delta. Proceedings of the 10th National Conference on Artificial Intelligence 1992, 171-176.
16. N.N. Schraudolph, J. Yu, D. Aberdeen, Fast online policy gradient learning with SMD gain vector adaptation, in: Advances in NIPS, vol. 18, 2006, pp. 1185-1192.
17. Noda I. Recursive adaptation of stepsize parameter for non-stationary environments. Principles of Practice in Multi-Agent Systems 2009, 525-533.
18. Wawrzyński P. Fixed point method of step-size estimation for on-line neural network training. WCCI 2010 IEEE World Congress on Computational Intelligence 2010, 2012-2017.
19. A. Frank, A. Asuncion, UCI machine learning repository, 2010.
20. Kushner H.J., Yin G. Stochastic Approximation Algorithms and Applications 1997, Springer-Verlag, New York.
21. Sunehag P., Trumpf J., Vishwanathan S., Schraudolph N. Variable metric stochastic approximation theory. 12th International Conference on Artificial Intelligence and Statistics 2009, 560-566.
22. Wang Z., Wang Y., Liu Y. Global synchronization for discrete-time stochastic complex networks with randomly occurred nonlinearities and mixed time-delays. IEEE Transactions on Neural Networks 2010, 21(1):11-25.