The Computing Capacity of Three-Input Multiple-Valued One-Threshold Perceptrons

Authors:
Alioune Ngom;Ivan Stojmenović;Ratko Tošić
Affiliations:
Computer Science Department, 5115 Lambton Tower, University of Windsor, 401 Sunset Avenue, N9B 3P4 Windsor, Ontario, Canada. E-mail: angom@cs.uwindsor.ca;Computer Science Department, 150 MacDonald Hall, School of Information Technology and Engineering, University of Ottawa, Ottawa, Ontario K1N 9B4, Canada. E-mail: ivan@site.uottawa.ca
Venue:
Neural Processing Letters
Year:
2001

Citing 11
Cited 0

Synthesis of Multivalued Multithreshold Functions for CCD Implementation

IEEE Transactions on Computers
Algorithms in combinatorial geometry

Algorithms in combinatorial geometry
The Capacity of Multilevel Threshold Functions

IEEE Transactions on Pattern Analysis and Machine Intelligence
On the number of linear partitions of the (m,n-grid

Information Processing Letters
Computing with discrete multi-valued neurons

Journal of Computer and System Sciences
Learning with discrete multivalued neurons

Journal of Computer and System Sciences
Discrete neural computation: a theoretical foundation

Discrete neural computation: a theoretical foundation
Learning with Permutably Homogeneous Multiple-Valued Multiple-Threshold Perceptrons

Neural Processing Letters
Minimization of Multivalued Multithreshold Perceptrons using Genetic Algorithms

ISMVL '98 Proceedings of the The 28th International Symposium on Multiple-Valued Logic
On the Number of Multilinear Partitions and the Computing Capacity of Multiple-Valued Multiple-Threshold Perceptrons.

ISMVL '99 Proceedings of the Twenty Ninth IEEE International Symposium on Multiple-Valued Logic
Synthesis of multiple-valued logic functions by neural networks

Synthesis of multiple-valued logic functions by neural networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, an exact and general formula is derived for the number of linear partitions of a given point set V in three-dimensional space, depending on the configuration formed by the points of V. The set V can be a multi-set, that is it may contain points that coincide. Based on the formula, we obtain an efficient algorithm for counting the number of k-valued logic functions simulated by a three-input k-valued one-threshold perceptron.