Abstract
A new multilayer incremental neural network (MINN) architecture and its performance in classification of biomedical images is discussed. The MINN consists of an input layer, two hidden layers and an output layer. The first stage between the input and first hidden layer consists of perceptrons. The number of perceptrons and their weights are determined by defining a fitness function which is maximized by the genetic algorithm (GA). The second stage involves feature vectors which are the codewords obtained automaticaly after learning the first stage. The last stage consists of OR gates which combine the nodes of the second hidden layer representing the same class. The comparative performance results of the MINN and the backpropagation (BP) network indicates that the MINN results in faster learning, much simpler network and equal or better classification performance.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
A. S. Miller, B. H. Blott, T. K. Hames. Review of neurel network npplications in medical imaging and signal processing,Medical and Biological Engineering and Computing, vol. 30, pp. 449–464, September 1992.
D. L. Prados. New learning algorithm for training multilayered neural networks that use genetic algorithm techniques,Electronics Letters, vol. 28, no. 16, pp. 1560–1562, 30 July 1992.
J. Makhoul, A. El-Jaroudi, R. Schwartz. Formation of disconnected decision regions with a single hidden layer,IJCNN Int. Joint Conf. Neural Networks. vol. 1, pp. 445–460, 1989.
D.E. Goldberg,Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley, 1989.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Olmez, T., Yazgan, E. & Ersoy, O.K. A multilayer incremental neural network architecture for classification. Neural Process Lett 2, 5–9 (1995). https://doi.org/10.1007/BF02312348
Issue Date:
DOI: https://doi.org/10.1007/BF02312348