Integrating rules and neural computation
This paper introduces a hybrid system termed cascade ARTMAP that incorporates symbolic knowledge into neural network learning and recognition. Cascade ARTMAP, a generalization of fuzzy ARTMAP, represents rule-based knowledge explicitly and performs multistep inferencing. A rule insertion algorithm t...
Saved in:
Main Author: | |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
1995
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6826 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-7829 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-78292022-01-27T03:48:03Z Integrating rules and neural computation TAN, Ah-hwee This paper introduces a hybrid system termed cascade ARTMAP that incorporates symbolic knowledge into neural network learning and recognition. Cascade ARTMAP, a generalization of fuzzy ARTMAP, represents rule-based knowledge explicitly and performs multistep inferencing. A rule insertion algorithm translates if-then symbolic rules into cascade ARTMAP architecture. Besides that initializing networks with prior knowledge improves learning efficiency and predictive accuracy, the inserted symbolic knowledge can be refined and enhanced by the cascade ARTMAP learning algorithm. By preserving symbolic rule form during learning, the rules extracted from cascade ARTMAP can be compared directly with the originally inserted rules. A benchmark study on a DNA promoter recognition problem shows that with the added advantages of fast and incremental learning, cascade ARTMAP produces performance superior to that of an alternative hybrid system. 1995-11-27T08:00:00Z text https://ink.library.smu.edu.sg/sis_research/6826 info:doi/10.1109/ICNN.1995.488893 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Databases and Information Systems |
spellingShingle |
Databases and Information Systems TAN, Ah-hwee Integrating rules and neural computation |
description |
This paper introduces a hybrid system termed cascade ARTMAP that incorporates symbolic knowledge into neural network learning and recognition. Cascade ARTMAP, a generalization of fuzzy ARTMAP, represents rule-based knowledge explicitly and performs multistep inferencing. A rule insertion algorithm translates if-then symbolic rules into cascade ARTMAP architecture. Besides that initializing networks with prior knowledge improves learning efficiency and predictive accuracy, the inserted symbolic knowledge can be refined and enhanced by the cascade ARTMAP learning algorithm. By preserving symbolic rule form during learning, the rules extracted from cascade ARTMAP can be compared directly with the originally inserted rules. A benchmark study on a DNA promoter recognition problem shows that with the added advantages of fast and incremental learning, cascade ARTMAP produces performance superior to that of an alternative hybrid system. |
format |
text |
author |
TAN, Ah-hwee |
author_facet |
TAN, Ah-hwee |
author_sort |
TAN, Ah-hwee |
title |
Integrating rules and neural computation |
title_short |
Integrating rules and neural computation |
title_full |
Integrating rules and neural computation |
title_fullStr |
Integrating rules and neural computation |
title_full_unstemmed |
Integrating rules and neural computation |
title_sort |
integrating rules and neural computation |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
1995 |
url |
https://ink.library.smu.edu.sg/sis_research/6826 |
_version_ |
1770576076698812416 |