论文信息 - Sparselized higher-order neural network and its pruning algorithm

Sparselized higher-order neural network and its pruning algorithm

In this paper, the fully-connected higher-order neuron and sparselized higher-order neuron are introduced, the mapping capabilities of the fully-connected higher-order neural networks are investigated, and that arbitrary Boolean function defined from (0,1)/sup N/ can be realized by fully-connected higher-order neural networks is proved. Based on this, in order to simplify the networks' architecture, a pruning algorithm of eliminating the redundant connection weights is also proposed, which can be applied to the implementation of sparselized higher-order neural classifier and other networks. The simulated results show the effectiveness of the algorithm.

[1] Shun-ichi Amari,et al. Dualistic geometry of the manifold of higher-order neurons , 1991, Neural Networks.

[2] Pierre Baldi,et al. Neural networks, orientations of the hypercube, and algebraic threshold functions , 1988, IEEE Trans. Inf. Theory.

[3] C. L. Giles,et al. Second-order recurrent neural networks for grammatical inference , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[4] Rolf Eckmiller,et al. Structural adaptation of parsimonious higher-order neural classifiers , 1994, Neural Networks.

[5] M.R. Azimi-Sadjadi,et al. Detection of dim targets in high cluttered background using high order correlation neural network , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[6] Colin Giles,et al. Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.