DocumentCode :
1242262
Title :
Analysis and synthesis of a class of discrete-time neural networks with multilevel threshold neurons
Author :
Si, Jennie ; Michel, Anthony N.
Author_Institution :
Dept. of Electr. Eng., Notre Dame Univ., IN, USA
Volume :
6
Issue :
1
fYear :
1995
fDate :
1/1/1995 12:00:00 AM
Firstpage :
105
Lastpage :
116
Abstract :
In contrast to the usual types of neural networks which utilize two states for each neuron, a class of synchronous discrete-time neural networks with multilevel threshold neurons is developed. A qualitative analysis and a synthesis procedure for the class of neural networks considered constitute the principal contributions of this paper. The applicability of the present class of neural networks is demonstrated by means of a gray level image processing example, where each neuron can assume one of sixteen values. When compared to the usual neural networks with two state neurons, networks which are endowed with multilevel neurons will, in general, for a given application, require fewer neurons and thus fewer interconnections. This is an important consideration in VLSI implementation
Keywords :
computer vision; image processing; network analysis; network synthesis; neural nets; discrete-time neural networks; gray level image processing; multilevel threshold neurons; network synthesis; qualitative analysis; Artificial neural networks; Associative memory; Books; Helium; Image processing; Network synthesis; Neural networks; Neurons; Optical feedback; Very large scale integration;
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/72.363445
Filename :
363445
Link To Document :
بازگشت