Supervised learning on a Fuzzy Petri Net

Amit Konar; Uday Kumar Chakraborty; Paul P. Wang

doi:10.1016/j.ins.2004.05.008

Supervised learning on a Fuzzy Petri Net

Amit Konar, Uday Kumar Chakraborty, Paul P. Wang

University of Missouri-St. Louis

Research output: Contribution to journal › Article › peer-review

Abstract

Feed-forward neural networks used for pattern classification generally have one input layer, one output layer and several hidden layers. The hidden layers in these networks add extra non-linearity for realization of precise functional mapping between the input and the output layers, but semantic relations of the hidden layers with their

predecessor and successor layers cannot be justified. This paper presents a novel scheme for supervised learning on a fuzzy Petri net that provides semantic justification of the hidden layers, and is capable of approximate reasoning and learning from noisy training instances. An algorithm for training a feed-forward fuzzy Petri net and an analysis of its convergence have been presented in the paper. The paper also examines the scope of the learning algorithm in object recognition from 2D geometric views.

Original language	American English
Journal	Information Sciences
Volume	172
DOIs	https://doi.org/10.1016/j.ins.2004.05.008
State	Published - Jun 1 2005

Disciplines

Computer Sciences
Artificial Intelligence and Robotics

Access to Document

10.1016/j.ins.2004.05.008License: Unspecified

Cite this

@article{762f53ab2ca44ebbbd2c2491caa0d517,

title = "Supervised learning on a Fuzzy Petri Net",

abstract = " Feed-forward neural networks used for pattern classification generally have one input layer, one output layer and several hidden layers. The hidden layers in these networks add extra non-linearity for realization of precise functional mapping between the input and the output layers, but semantic relations of the hidden layers with their predecessor and successor layers cannot be justified. This paper presents a novel scheme for supervised learning on a fuzzy Petri net that provides semantic justification of the hidden layers, and is capable of approximate reasoning and learning from noisy training instances. An algorithm for training a feed-forward fuzzy Petri net and an analysis of its convergence have been presented in the paper. The paper also examines the scope of the learning algorithm in object recognition from 2D geometric views.",

author = "Amit Konar and Chakraborty, {Uday Kumar} and Wang, {Paul P.}",

year = "2005",

month = jun,

day = "1",

doi = "10.1016/j.ins.2004.05.008",

language = "American English",

volume = "172",

journal = "Information Sciences",

}

TY - JOUR

T1 - Supervised learning on a Fuzzy Petri Net

AU - Konar, Amit

AU - Chakraborty, Uday Kumar

AU - Wang, Paul P.

PY - 2005/6/1

Y1 - 2005/6/1

N2 - Feed-forward neural networks used for pattern classification generally have one input layer, one output layer and several hidden layers. The hidden layers in these networks add extra non-linearity for realization of precise functional mapping between the input and the output layers, but semantic relations of the hidden layers with their predecessor and successor layers cannot be justified. This paper presents a novel scheme for supervised learning on a fuzzy Petri net that provides semantic justification of the hidden layers, and is capable of approximate reasoning and learning from noisy training instances. An algorithm for training a feed-forward fuzzy Petri net and an analysis of its convergence have been presented in the paper. The paper also examines the scope of the learning algorithm in object recognition from 2D geometric views.

AB - Feed-forward neural networks used for pattern classification generally have one input layer, one output layer and several hidden layers. The hidden layers in these networks add extra non-linearity for realization of precise functional mapping between the input and the output layers, but semantic relations of the hidden layers with their predecessor and successor layers cannot be justified. This paper presents a novel scheme for supervised learning on a fuzzy Petri net that provides semantic justification of the hidden layers, and is capable of approximate reasoning and learning from noisy training instances. An algorithm for training a feed-forward fuzzy Petri net and an analysis of its convergence have been presented in the paper. The paper also examines the scope of the learning algorithm in object recognition from 2D geometric views.

UR - http://dz5.pl/ti/Materialy/Supervised%20Learning%20On%20A%20Fuzzy%20Petri%20Net.pdf

U2 - 10.1016/j.ins.2004.05.008

DO - 10.1016/j.ins.2004.05.008

M3 - Article

VL - 172

JO - Information Sciences

JF - Information Sciences

ER -

Supervised learning on a Fuzzy Petri Net

Abstract

Disciplines

Access to Document

Other files and links

Cite this