Morphological associative memories
- 1 March 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 9 (2), 281-293
- https://doi.org/10.1109/72.661123
Abstract
The theory of artificial neural networks has been successfully applied to a wide variety of pattern recognition problems. In this theory, the first step in computing the next state of a neuron or in performing the next layer neural network computation involves the linear operation of multiplying neural values by their synaptic strengths and adding the results. A nonlinear activation function usually follows the linear operation in order to provide for nonlinearity of the network and set the next state of the neuron. In this paper we introduce a novel class of artificial neural networks, called morphological neural networks, in which the operations of multiplication and addition are replaced by addition and maximum (or minimum), respectively. By taking the maximum (or minimum) of sums instead of the sum of products, morphological network computation is nonlinear before possible application of a nonlinear activation function. As a consequence, the properties of morphological neural networks are drastically different than those of traditional neural network models. The main emphasis of the research presented here is on morphological associative memories. We examine the computing and storage capabilities of morphological associative memories and discuss differences between morphological models and traditional semilinear models such as the Hopfield net.Keywords
This publication has 24 references indexed in Scilit:
- Novel Neural Network Models for Computing Homothetic Invariances: An Image Algebra NotationJournal of Mathematical Imaging and Vision, 1997
- An introduction to morphological neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Image algebra networks for pattern classificationPublished by SPIE-Intl Soc Optical Eng ,1994
- Morphology neural networks: An introduction with applicationsCircuits, Systems, and Signal Processing, 1993
- Simulated annealing and morphology neural networksPublished by SPIE-Intl Soc Optical Eng ,1992
- Recent Developments in Image AlgebraAdvances in Electronics and Electron Physics, 1991
- Theory of morphological neural networksPublished by SPIE-Intl Soc Optical Eng ,1990
- Image algebra: An overviewComputer Vision, Graphics, and Image Processing, 1990
- Image Algebra And Its Relationship To Neural NetworksPublished by SPIE-Intl Soc Optical Eng ,1989
- Neural network models of learning and adaptationPhysica D: Nonlinear Phenomena, 1986