论文信息 - Pruning in Recurrent Neural Networks

Pruning in Recurrent Neural Networks

Recurrent neural networks are attracting considerable interest within the neural network domain especially because of their potential in such problems as pattern completion and temporal sequence processing (Almeida, 1987; Hertz et al., 1991). As for feed-forward networks, in virtually all problems of interest the proper number of hidden units is not known in advance, and usually this turns out to be a trade-off between generalization and learning abilities (Hertz et al., 1991). One popular way of solving this problem involves training an over-dimensioned network and then pruning excessive units (Sietsma and Dow, 1988).

[1] Å. Björck,et al. Accelerated projection methods for computing pseudoinverse solutions of systems of linear equations , 1979 .

[2] Fernando J. Pineda,et al. Dynamics and architecture for neural computation , 1988, J. Complex..

[3] M. A. Bush,et al. How limited training data can allow a neural network to outperform an 'optimal' statistical classifier , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[4] L. B. Almeida. A learning rule for asynchronous perceptrons with feedback in a combinatorial environment , 1990 .

[5] Anders Krogh,et al. Introduction to the theory of neural computation , 1994, The advanced book program.

[6] Anna Maria Fanelli,et al. A Method of Pruning Layered Feed-Forward Neural Networks , 1993, IWANN.

[7] Giovanna Castellano,et al. An empirical comparison of node pruning methods for layered feedforward neural networks , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[8] Alberto Prieto,et al. New Trends in Neural Computation , 1993 .

[9] R. Palmer,et al. Introduction to the theory of neural computation , 1994, The advanced book program.