Simple and conditioned adaptive behavior from Kalman filter trained recurrent networks

We illustrate the ability of a fixed-weight neural network, trained with Kalman filter methods, to perform tasks that are usually entrusted to an explicitly adaptive system. Following a simple example, we demonstrate that such a network can be trained to exhibit input-output behavior that depends on which of two conditioning tasks was performed a substantial number of time steps in the past. This behavior can also be made to survive an intervening interference task.

[1]  Danil V. Prokhorov,et al.  Adaptive behavior with fixed weights in RNN: an overview , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[2]  Danil V. Prokhorov,et al.  Recurrent neural network training by nprKF joint estimation , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[3]  S. Haykin.  Kalman Filtering and Neural Networks , 2001 .

[4]  Rudolph van der Merwe,et al.  The Unscented Kalman Filter , 2002 .

[5]  Richard S. Sutton,et al.  Neural networks for control , 1990 .

[6]  Lee A. Feldkamp,et al.  Adaptation from fixed weight dynamic networks , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[7]  Lee A. Feldkamp,et al.  Fixed-weight controller for multiple systems , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[8]  Lee A. Feldkamp,et al.  Adaptive Behavior from Fixed Weight Networks , 1997, Inf. Sci..

[9]  Rudolph van der Merwe,et al.  Gaussian mixture sigma-point particle filters for sequential probabilistic inference in dynamic state-space models , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[10]  Danil V. Prokhorov,et al.  Neural network training with the nprKF , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[11]  A. Steven Younger,et al.  Fixed-weight on-line learning , 1999, IEEE Trans. Neural Networks.

[12]  Sepp Hochreiter,et al.  Learning to Learn Using Gradient Descent , 2001, ICANN.

[13]  Ronald J. Williams,et al.  Adaptive state representation and estimation using recurrent connectionist networks , 1990 .

[14]  G. V. Puskorius,et al.  A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering, and classification , 1998, Proc. IEEE.