Abstract:
Supervised Adaptive Resonance Theory is a family of neural networks that performs incremental supervised learning of recognition categories (pattern classes) and multidimensional maps of both binary and analog patterns. This chapter highlights that the supervised ART architecture is compatible with IF-THEN rule-based symbolic representation. Speci cally, the knowledge learned by a supervised ART system can be readily translated into rules for interpretation. Similarly, a priori domain knowledge in the form of IF-THEN rules can be converted into a supervised ART architecture. Not only does initializing networks with prior knowledge improve predictive accuracy and learning e ciency, the inserted symbolic knowledge can also be re ned and enhanced by the supervised ART learning algorithm. By preserving symbolic rule form during learning, the rules extracted from a supervised ART system can be compared directly with the originally inserted rules. 1
Citations
|
2489
|
Induction of Decision Trees
– Quinlan
- 1986
|
|
655
|
UCI Repository of Machine Learning Databases [machine-readable data repository
– Murphy, Aha
- 1992
|
|
302
|
A Massively Parallel Architecture for a SelfOrganizing Neural
– Carpenter, Grossberg
- 1987
|
|
177
|
Fuzzy ARTMAP: A Neural Network Architecture for Incremental Learning of Analog Multidimensional Maps
– Carpenter, Grossberg, et al.
- 1992
|
|
170
|
Extracting refined rules from knowledge-based neural networks
– Towell, Shavlik
- 1993
|
|
133
|
Fuzzy ART: fast stable learning and categorization of analog patterns by an adaptive resonance system
– Carpenter, Grossberg, et al.
- 1991
|
|
51
|
Interpretation of artificial neural networks: Mapping Knowledge Based Neural Networks into rules
– Towell, Shawlik
- 1992
|
|
38
|
Network structuring and training using rule-based knowledge
– Tresp, Hollatz, et al.
- 1993
|
|
35
|
Refinement of Approximately Correct Domain Theories by Knowledge-Based Neural Networks
– Towell, Shavlik, et al.
- 1990
|
|
32
|
Backpropagation learning in expert networks
– Lacher, Hruska, et al.
- 1992
|
|
29
|
Application of neural networks and other machine learning algorithms to DNA sequence analysis
– Lapedes, Barnes, et al.
- 1989
|
|
25
|
Adaptive resonance associative map
– Tan
- 1995
|
|
23
|
Rule extraction: From neural architecture to symbolic representation
– Carpenter, Tan
- 1995
|
|
21
|
Cascade ARTMAP: Integrating neural computation and symbolic knowledge processing
– Tan
- 1997
|
|
12
|
Escherichia Coli Promoters: I. Consensus as it relates to spacing class, specificity, repeat substructure, and three dimensional orgainzation
– O'Neill
- 1989
|
|
12
|
Learning user profile for personal information dissemination
– Tan, Teo
- 1998
|
|
9
|
Escherichia coli promoters II. A spacing class-dependent promoter search protocol
– O'Neill, Chiafari
- 1989
|
|
9
|
Extracting re ned rules from knowledge-based neural networks
– Towell, Shavlik
- 1993
|
|
6
|
ARTMAP: Supervised real time learning and classification by a self-organizing neural network
– Carpenter, Grossberg, et al.
- 1991
|
|
6
|
Interpretation of arti cial neural networks: Mapping knowledge-based neural networks into rules
– Towell, Shavlik
- 1992
|
|
5
|
Determination of eucaryotic protein coding regions using neural networks and information theory
– Farber, Lapedes, et al.
- 1992
|
|
3
|
Re nement of approximately correct domain theories by knowledgebased neural networks
– Towell, Shavlik, et al.
- 1990
|
|
1
|
Mapping rule-based knowledge into neural architecture
– Fu, Fu
- 1990
|
|
1
|
Learning user pro les for personalized information dissemination
– Tan, Teo
- 1998
|
|
1
|
Mathematical Methods for DNA sequences. Boca
– Waterman
- 1989
|
