ART Properties of Interest in Engineering Applications

Donald C. Wunsch

doi:10.1109/IJCNN.2009.5179094

ART Properties of Interest in Engineering Applications

Donald C. Wunsch

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

Abstract

This paper briefly summarizes some valuable properties of ART architectures that are advantageous in engineering applications, and outlines some areas of likely future progress, together with their motivations. Some of ART's advantages, such as its stability, biological plausibility, and responsiveness to the stability-plasticity dilemma, are well-described in the literature. This paper's focus will be on the advantages of scalability, speed, configurability, potential for parallelization, and ability to interpret the results. A valuable new area of innovation will be the application of ART to more generalized data structures such as trees and grammars. Continued progress on distributed representations would be valuable because of increased data representation capability, both in terms of system capacity and template complexity. Another valuable area of progress would be removal of the dichotomy between match-based and error-based learning.

Original language	American English
Journal	Proceedings of the International Joint Conference on Neural Networks
DOIs	https://doi.org/10.1109/IJCNN.2009.5179094
State	Published - Jan 1 2009

Disciplines

Electrical and Computer Engineering

Access to Document

10.1109/IJCNN.2009.5179094License: Unspecified

https://doi.org/10.1109/IJCNN.2009.5179094

Cite this

@article{28d191fe2d4b40f39714a7fc0880cd38,

title = "ART Properties of Interest in Engineering Applications",

abstract = " This paper briefly summarizes some valuable properties of ART architectures that are advantageous in engineering applications, and outlines some areas of likely future progress, together with their motivations. Some of ART's advantages, such as its stability, biological plausibility, and responsiveness to the stability-plasticity dilemma, are well-described in the literature. This paper's focus will be on the advantages of scalability, speed, configurability, potential for parallelization, and ability to interpret the results. A valuable new area of innovation will be the application of ART to more generalized data structures such as trees and grammars. Continued progress on distributed representations would be valuable because of increased data representation capability, both in terms of system capacity and template complexity. Another valuable area of progress would be removal of the dichotomy between match-based and error-based learning.",

author = "Wunsch, \{Donald C.\}",

year = "2009",

month = jan,

day = "1",

doi = "10.1109/IJCNN.2009.5179094",

language = "American English",

journal = "Proceedings of the International Joint Conference on Neural Networks",

issn = "2161-4407",

}

TY - JOUR

T1 - ART Properties of Interest in Engineering Applications

AU - Wunsch, Donald C.

PY - 2009/1/1

Y1 - 2009/1/1

N2 - This paper briefly summarizes some valuable properties of ART architectures that are advantageous in engineering applications, and outlines some areas of likely future progress, together with their motivations. Some of ART's advantages, such as its stability, biological plausibility, and responsiveness to the stability-plasticity dilemma, are well-described in the literature. This paper's focus will be on the advantages of scalability, speed, configurability, potential for parallelization, and ability to interpret the results. A valuable new area of innovation will be the application of ART to more generalized data structures such as trees and grammars. Continued progress on distributed representations would be valuable because of increased data representation capability, both in terms of system capacity and template complexity. Another valuable area of progress would be removal of the dichotomy between match-based and error-based learning.

AB - This paper briefly summarizes some valuable properties of ART architectures that are advantageous in engineering applications, and outlines some areas of likely future progress, together with their motivations. Some of ART's advantages, such as its stability, biological plausibility, and responsiveness to the stability-plasticity dilemma, are well-described in the literature. This paper's focus will be on the advantages of scalability, speed, configurability, potential for parallelization, and ability to interpret the results. A valuable new area of innovation will be the application of ART to more generalized data structures such as trees and grammars. Continued progress on distributed representations would be valuable because of increased data representation capability, both in terms of system capacity and template complexity. Another valuable area of progress would be removal of the dichotomy between match-based and error-based learning.

UR - https://scholarsmine.mst.edu/ele_comeng_facwork/613

UR - https://doi.org/10.1109/IJCNN.2009.5179094

U2 - 10.1109/IJCNN.2009.5179094

DO - 10.1109/IJCNN.2009.5179094

M3 - Article

SN - 2161-4407

JO - Proceedings of the International Joint Conference on Neural Networks

JF - Proceedings of the International Joint Conference on Neural Networks

ER -

ART Properties of Interest in Engineering Applications

Abstract

Disciplines

Access to Document

Other files and links

Fingerprint

Cite this