论文信息 - The autoregressive backpropagation algorithm

The autoregressive backpropagation algorithm

Describes an extension to error backpropagation that allows the nodes in a neural network to encode state information in an autoregressive 'memory'. This neural model gives such networks the ability to learn to recognize sequences and context-sensitive patterns. Building upon the work of A. Wieland (1990) concerning nodes with a single feedback connection, the authors generalize the method to n feedback connections and address stability issues. The learning algorithm is derived, and a few applications are presented.<<ETX>>

R. R. Leighton | B. C. Conrath

[1] Richard S. Sutton,et al. Learning and Sequential Decision Making , 1989 .

[2] K. Lang,et al. Learning to tell two spirals apart , 1988 .

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

[4] Barak A. Pearlmutter. Dynamic recurrent neural networks , 1990 .

[5] Fernando J. Pineda,et al. Generalization of Back propagation to Recurrent and Higher Order Neural Networks , 1987, NIPS.

[6] Paul J. Werbos,et al. Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[7] Shien-Ming Wu,et al. Time series and system analysis with applications , 1983 .

[8] Luís B. Almeida,et al. A learning rule for asynchronous perceptrons with feedback in a combinatorial environment , 1990 .