Towards continuously learning neural networks
暂无分享,去创建一个
A modular three layer variable structure feedforward network capable of learning by stages is proposed. It consists of a first layer of threshold units, and two subsequent layers of logical gates. The threshold units have a vectorial threshold (instead of a simple scalar), which gives them a spatial reference within the input space. They are trained using the method of centroids, developed by the authors. The modularity of this arrangement allows progressive learning, and the extra units are added as needed, to match the complexity of the problem. The system was tested both with real data and with artificially generated data, to assess its potential. Finally, ways of expanding on the present model are discussed.
[1] P. D. Keefe. Observations concerning shape variation in wheat grains. , 1990 .
[2] S. R. Draper,et al. The measurement of new characters for cultivar identification in wheat using machine vision , 1986 .
[3] Rui J. P. de Figueiredo,et al. An evolution-oriented learning algorithm for the optimal interpolative net , 1992, IEEE Trans. Neural Networks.