Learning State Space Trajectories in Recurrent Neural Networks

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 cycles are shown. This type of recurrent network seems particularly suited for temporally continuous domains, such as signal processing, control, and speech.

[1]  John B. Shoven,et al.  I , Edinburgh Medical and Surgical Journal.

[2]  A. E. Bryson,et al.  A Steepest-Ascent Method for Solving Optimum Programming Problems , 1962 .

[3]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[4]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[5]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[6]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[7]  J. M. Sanz-Serna,et al.  On simple moving grid methods for one-dimensional evolutionary partial differential equations , 1988 .

[8]  Carsten Peterson,et al.  A Mean Field Theory Learning Algorithm for Neural Networks , 1987, Complex Syst..

[9]  Pineda,et al.  Generalization of back-propagation to recurrent neural networks. , 1987, Physical review letters.

[10]  Patrice Y. Simard,et al.  Analysis of Recurrent Backpropagation , 1988 .

[11]  PAUL J. WERBOS,et al.  Generalization of backpropagation with application to a recurrent gas market model , 1988, Neural Networks.

[12]  Barak A. Pearlmutter.  Learning state space trajectories in recurrent neural networks : a preliminary report. , 1988 .

[13]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[14]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[15]  Michael I. Jordan.  Attractor dynamics and parallelism in a connectionist sequential machine , 1990 .