| Self-organizing ARTMAP rule discovery. | |
| | |
MedLine Citation:
|
PMID: 21982690 Owner: NLM Status: Publisher |
Abstract/OtherAbstract:
|
The Self-Organizing ARTMAP Rule Discovery (SOARD) system derives relationships among recognition classes during online learning. SOARD training on input/output pairs produces the basic competence of direct recognition of individual class labels for new test inputs. As a typical supervised system, it learns many-to-one maps, which recognize different inputs (Spot, Rex) as belonging to one class (dog). As an ARTMAP system, it also learns one-to-many maps, allowing a given input (Spot) to learn a new class (animal) without forgetting its previously learned output (dog), even as it corrects erroneous predictions (cat). As it learns individual input/output class predictions, SOARD employs distributed code representations that support online rule discovery. When the input Spot activates the classes dogand animal, confidence in the rule dog→animal begins to grow. When other inputs simultaneously activate classes cat and animal, confidence in the converse rule, animal→dog, decreases. Confidence in a self-organized rule is encoded as the weight in a path from one class node to the other. An experience-based mechanism modulates the rate of rule learning, to keep inaccurate predictions from creating false rules during early learning. Rules may be excitatory or inhibitory so that rule-based activation can add missing classes and remove incorrect ones. SOARD rule activation also enables inputs to learn to make direct predictions of output classes that they have never experienced during supervised training. When input Rex activates its learned class dog, the rule dog→animal indirectly activates the output class animal. The newly activated class serves as a teaching signal which allows input Rex to learn direct activation of the output class animal. Simulations using small-scale and large-scale datasets demonstrate functional properties of the SOARD system in both spatial and time-series domains. |
| | |
Authors:
|
Gail A Carpenter; Santiago Olivera |
Publication Detail:
|
Type: JOURNAL ARTICLE Date: 2011-9-17 |
Journal Detail:
|
Title: Neural networks : the official journal of the International Neural Network Society Volume: - ISSN: 1879-2782 ISO Abbreviation: - Publication Date: 2011 Sep |
Date Detail:
|
Created Date: 2011-10-10 Completed Date: - Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 8805018 Medline TA: Neural Netw Country: - |
Other Details:
|
Languages: ENG Pagination: - Citation Subset: - |
Copyright Information:
|
Copyright © 2011 Elsevier Ltd. All rights reserved. |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
|
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Risk factors for hip-related clinical signs in a prospective cohort study of four large dog breeds i...
Next Document: Three-Dimensional Reconstruction of Maxillae Using Spiral Computed Tomography and Its Application in...