Improved network inversion technique for query learning application to automated cytology screening

An improved neural network inversion technique that scales the search vector in accordance with the geometry of the problem has been developed. It searches in the direction of the gradient with a vector whose size is inversely related to the size of the gradient. To avoid unlimited growth of the search vector where the gradient is small, an upper bound is set on the size of the search vector. The network was trained by backpropagation and the training was halted when the network produced no error on the training set, where the output was categorized by binary thresholding. The results show the superior performance of the improved method. The technique was applied to automated cytology screening. A set of 400 object feature vectors randomly selected from a large database of 1929 feature vectors served as the initial training data.<<ETX>>

[1]  Jean Serra,et al.  Image Analysis and Mathematical Morphology , 1983 .

[2]  A. Linden,et al.  Inversion of multilayer nets , 1989, International 1989 Joint Conference on Neural Networks.

[3]  J. Taylor,et al.  Computer recognition of ectocervical cells. Classification accuracy and spatial resolution. , 1977, Acta cytologica.

[4]  R. Haralick,et al.  Morphologic edge detection , 1986, IEEE J. Robotics Autom..

[5]  J. Tucker.  An image analysis system for cervical cytology automation using nuclear DNA content. , 1979, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[6]  Fernand Meyer.  Automatic screening of cytological specimens , 1986 .

[7]  Jenq-Neng Hwang,et al.  Classification boundaries and gradients of trained multilayer perceptrons , 1990, IEEE International Symposium on Circuits and Systems.

[8]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[9]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .

[10]  Jack Sklansky,et al.  Locally Trained Piecewise Linear Classifiers , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  S. Y. Kung,et al.  An algebraic projection analysis for optimal hidden units size and learning rates in back-propagation learning , 1988, IEEE 1988 International Conference on Neural Networks.

[12]  Jenq-Neng Hwang,et al.  Query-based learning applied to partially trained multilayer perceptrons , 1991, IEEE Trans. Neural Networks.