Morphological neural networks
Conference
·
OSTI ID:466457
- Univ. of Florida, Gainesville, FL (United States)
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. Thresholding usually follows the linear operation in order to provide for nonlinearity of the network. In this paper we introduce a novel class of 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 thresholding. As a consequence, the properties of morphological neural networks are drastically different than those of traditional neural network models. In this paper we consider some of these differences and provide some particular examples of morphological neural network.
- OSTI ID:
- 466457
- Report Number(s):
- CONF-9610138--
- Country of Publication:
- United States
- Language:
- English
Similar Records
Optimal neural computations require analog processors
Electrically modifiable nonvolatile sonos synapses for electronic neural networks. Semiannual technical report, 1 Mar-1 Sep 91
Neural networks and their potential application to nuclear power plants
Conference
·
Wed Dec 30 23:00:00 EST 1998
·
OSTI ID:334348
Electrically modifiable nonvolatile sonos synapses for electronic neural networks. Semiannual technical report, 1 Mar-1 Sep 91
Technical Report
·
Sun Sep 01 00:00:00 EDT 1991
·
OSTI ID:6132894
Neural networks and their potential application to nuclear power plants
Conference
·
Mon Dec 31 23:00:00 EST 1990
·
OSTI ID:6926345