Learning with permutably homogeneous multiple-valued multiple-threshold perceptrons

Alioune Ngom; Corina Reischer; Dan A. Simovici; Ivan Stojmenovic

Learning with permutably homogeneous multiple-valued multiple-threshold perceptrons

Alioune Ngom
, Corina Reischer
, Dan A. Simovici
, Ivan Stojmenovic

Computer Science

Université du Québec à Trois-Rivières

Research output: Contribution to journal › Conference article › peer-review

Abstract

The (k, s)-perceptrons partition the input space {0, ..., k-1}ⁿ into s+1 regions using s parallel hyperplanes. Their learning abilities are examined in this paper. The previously studied homogeneous (k, k-1)-perceptron learning algorithm is generalized to the permutably homogeneous (k, s)-perceptron learning algorithm with guaranteed convergence property. We also introduce a powerful learning method that learns any permutably homogeneously separable k-valued logic function given as input.

Original language	English
Pages (from-to)	161-166
Number of pages	6
Journal	Proceedings of The International Symposium on Multiple-Valued Logic
State	Published - 1998
Event	Proceedings of the 1998 28th International Symposium on Multiple-Valued Logic - Fukuoka, Jpn Duration: May 27 1998 → May 29 1998

ASJC Scopus Subject Areas

General Computer Science
General Mathematics

Cite this

@article{5b4bf2694c564637a6963116b9ec4715,

title = "Learning with permutably homogeneous multiple-valued multiple-threshold perceptrons",

abstract = "The (k, s)-perceptrons partition the input space \{0, ..., k-1\}n into s+1 regions using s parallel hyperplanes. Their learning abilities are examined in this paper. The previously studied homogeneous (k, k-1)-perceptron learning algorithm is generalized to the permutably homogeneous (k, s)-perceptron learning algorithm with guaranteed convergence property. We also introduce a powerful learning method that learns any permutably homogeneously separable k-valued logic function given as input.",

author = "Alioune Ngom and Corina Reischer and Simovici, \{Dan A.\} and Ivan Stojmenovic",

year = "1998",

language = "English",

pages = "161--166",

journal = "Proceedings of The International Symposium on Multiple-Valued Logic",

issn = "0195-623X",

publisher = "IEEE Computer Society",

note = "Proceedings of the 1998 28th International Symposium on Multiple-Valued Logic ; Conference date: 27-05-1998 Through 29-05-1998",

}

TY - JOUR

T1 - Learning with permutably homogeneous multiple-valued multiple-threshold perceptrons

AU - Ngom, Alioune

AU - Reischer, Corina

AU - Simovici, Dan A.

AU - Stojmenovic, Ivan

PY - 1998

Y1 - 1998

N2 - The (k, s)-perceptrons partition the input space {0, ..., k-1}n into s+1 regions using s parallel hyperplanes. Their learning abilities are examined in this paper. The previously studied homogeneous (k, k-1)-perceptron learning algorithm is generalized to the permutably homogeneous (k, s)-perceptron learning algorithm with guaranteed convergence property. We also introduce a powerful learning method that learns any permutably homogeneously separable k-valued logic function given as input.

AB - The (k, s)-perceptrons partition the input space {0, ..., k-1}n into s+1 regions using s parallel hyperplanes. Their learning abilities are examined in this paper. The previously studied homogeneous (k, k-1)-perceptron learning algorithm is generalized to the permutably homogeneous (k, s)-perceptron learning algorithm with guaranteed convergence property. We also introduce a powerful learning method that learns any permutably homogeneously separable k-valued logic function given as input.

UR - https://www.scopus.com/pages/publications/0031635405

UR - https://www.scopus.com/pages/publications/0031635405#tab=citedBy

M3 - Conference article

AN - SCOPUS:0031635405

SN - 0195-623X

SP - 161

EP - 166

JO - Proceedings of The International Symposium on Multiple-Valued Logic

JF - Proceedings of The International Symposium on Multiple-Valued Logic

T2 - Proceedings of the 1998 28th International Symposium on Multiple-Valued Logic

Y2 - 27 May 1998 through 29 May 1998

ER -

Learning with permutably homogeneous multiple-valued multiple-threshold perceptrons

Abstract

ASJC Scopus Subject Areas

Other files and links

Fingerprint

Cite this