Learning State Space Trajectories in Recurrent Neural Networks

@article{Pearlmutter1989LearningSS,
  title={Learning State Space Trajectories in Recurrent Neural Networks},
  author={Barak A. Pearlmutter},
  journal={Neural Computation},
  year={1989},
  volume={1},
  pages={263-269}
}
Many neural network learning procedures compute gradients of the errors on the output layer of units after they have settled to their final values. We describe a procedure for finding E/wij, where E is an error functional of the temporal trajectory of the states of a continuous recurrent network and wij are the weights of that network. Computing these quantities allows one to perform gradient descent in the weights to minimize E. Simulations in which networks are taught to move through limit… Expand
710 Citations
Generating network trajectories using gradient descent in state space
  • R. Hahnloser
  • Computer Science
  • 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227)
  • 1998
  • 1
A simplex optimization approach for recurrent neural network training and for learning time-dependent trajectory patterns
  • Y. C. Wong, M. Sundareshan
  • Computer Science
  • IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)
  • 1999
Recurrent neural networks for temporal learning of time series
  • 1
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
  • 3,447
A learning algorithm to teach spatiotemporal patterns to recurrent neural networks
  • M. Sato
  • Computer Science
  • Biological Cybernetics
  • 2004
  • 22
Bifurcations of Recurrent Neural Networks in Gradient Descent Learning
  • 34
Learning scheme for recurrent neural network by genetic algorithm
  • T. Fukuda, T. Kohno, T. Shibata
  • Computer Science
  • Proceedings of 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '93)
  • 1993
Recurrent Backpropagation and the Dynamical Approach to Adaptive Neural Computation
  • F. Pineda
  • Computer Science
  • Neural Computation
  • 1989
  • 181
  • PDF
Learning temporal patterns in recurrent neural networks
  • K. Doya
  • Computer Science
  • 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings
  • 1990
  • 7
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 26 REFERENCES
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
  • 3,447
  • Highly Influential
Generalization of back-propagation to recurrent neural networks.
  • Pineda
  • Computer Science, Medicine
  • Physical review letters
  • 1987
  • 867
Learning state space trajectories in recurrent neural networks : a preliminary report.
  • 110
  • PDF
Generalization of backpropagation with application to a recurrent gas market model
  • 811
  • PDF
Analysis of Recurrent Backpropagation
  • 16
  • Highly Influential
A Learning Algorithm for Boltzmann Machines
  • 3,149
  • PDF
Phoneme recognition using time-delay neural networks
  • 2,626
  • PDF
A Steepest-Ascent Method for Solving Optimum Programming Problems
  • 414
  • PDF
Optimization by Simulated Annealing
  • 37,567
  • PDF
...
1
2
3
...