论文信息 - A method for training recurrent neural networks for classification by building basins of attraction

A method for training recurrent neural networks for classification by building basins of attraction

Abstract The main contribution of this report is the suggestion, development, and trial of a new way of using a Hopfield network for classification. Rather than storing the members of the training sets (sets of exemplars) as stable points, a connection matrix is determined, using perceptron-type learning, such that the exemplars are put into basins of attraction. The elements from different training sets are placed in different basins of attraction, with usually more than one basin per training class. The attractors for the basins of attraction are determined at the same time that the exemplars are placed in these basins. An arbitrary element is then classified by the basin of attraction it falls into. The method is successfully applied to artificially generated classes and to the classification of cervical cells for cancer detection.

Roelof K. Brouwer

[1] B Palcic,et al. Comparison of three different methods for automated classification of cervical cells. , 1992, Analytical cellular pathology : the journal of the European Society for Analytical Cellular Pathology.

[2] H Banda-Gambao. Classification of cervical cells using computer vision and the frequency domain. , 1990 .

[3] Martin Hasler,et al. Recursive neural networks for associative memory , 1990, Wiley-interscience series in systems and optimization.

[4] Ciamac C. Moallemi,et al. Classifying cells for cancer diagnosis using neural networks , 1991, IEEE Expert.

[5] B. Allan. What managers really need to know about LANs , 1989, IEEE Network.

[6] Stephen J. McKenna,et al. Towards the automated prescreening of cervical smears , 1992 .

[7] Murray Smith,et al. Neural Networks for Statistical Modeling , 1993 .

[8] Daniel J. Amit,et al. Modeling brain function: the world of attractor neural networks, 1st Edition , 1989 .

[9] Ian W. Ricketts,et al. Cervical cell image inspection—a task for artificial neural networks , 1992 .

[10] Esther Levin,et al. A recurrent neural network: Limitations and training , 1990, Neural Networks.

[11] Stephen I. Gallant,et al. Perceptron-based learning algorithms , 1990, IEEE Trans. Neural Networks.

[12] Michael R. Davenport,et al. A Recurrent Neural Network Using Tri-State Hidden Neurons to Orthogonalize the Memory Space , 1989, Int. J. Neural Syst..