A Survey of Adaptive Resonance Theory Neural Network Models for Engineering Applications

Abstract

This survey samples from the ever-growing family of adaptive resonance theory (ART) neural network models used to perform the three primary machine learning modalities, namely, unsupervised, supervised and reinforcement learning. It comprises a representative list from classic to contemporary ART models, thereby painting a general picture of the architectures developed by researchers over the past 30 years. The learning dynamics of these ART models are briefly described, and their distinctive characteristics such as code representation, long-term memory, and corresponding geometric interpretation are discussed. Useful engineering properties of ART (speed, configurability, explainability, parallelization and hardware implementation) are examined along with current challenges. Finally, a compilation of online software libraries is provided. It is expected that this overview will be helpful to new and seasoned ART researchers.

Department(s)

Electrical and Computer Engineering

Research Center/Lab(s)

Center for High Performance Computing Research

Comments

This research was sponsored by the Missouri University of Science and Technology, USA Mary K. Finley Endowment and Intelligent Systems Center; the Coordenacao de Aperfeiçoamento de Pessoal de Nível Superior – Brazil (CAPES) – Finance code BEX 13494/13-9 ; the Army Research Laboratory (ARL) and the Lifelong Learning Machines program from DARPA /MTO, USA and it was accomplished under Cooperative Agreement Number W911NF-18-2-0260.

Keywords and Phrases

Adaptive Resonance Theory; Classification; Clustering; Regression; Reinforcement Learning; Survey

International Standard Serial Number (ISSN)

0893-6080

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2019 Elsevier Ltd, All rights reserved.

Publication Date

01 Dec 2019

PubMed ID

31610899

Link to Full Text

Share

 
COinS