Name
Abstract | ||
|---|---|---|
This article introduces Adaptive Resonance Theory 2-A (ART 2-A), an efficient algorithm that emulates the self-organizing pattern recognition and hypothesis testing properties of the ART 2 neural network architecture, but at a speed two to three orders of magnitude faster. Analysis and simulations show how the ART 2-A systems correspond to ART 2 dynamics at both the fast-learn limit and at intermediate learning rates. Intermediate learning rates permit fast commitment of category nodes but slow recoding, analogous to properties of word frequency effects, encoding specificity effects, and episodic memory. Better noise tolerance is hereby achieved without a loss of learning stability. The ART 2 and ART 2-A systems are contrasted with the leader algorithm. The speed of ART 2-A makes practical the use of ART 2 modules in large scale neural computation. |
Year | DOI | Venue |
|---|---|---|
1991 | 10.1016/0893-6080(91)90045-7 | Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference |
Keywords | Field | DocType |
pattern recognition,adaptive resonance algorithm,rapid category,art,neural networks,adaptive resonance,art 2-a,fast learning,category formation,neural network,word frequency,resonance,hypothesis test,category learning,neural nets,frequency,stability,hypothesis testing,encoding,self organization,episodic memory,adaptive systems | Computer science,Concept learning,Models of neural computation,Artificial intelligence,Artificial neural network,Statistical hypothesis testing,Word lists by frequency,Pattern recognition,Adaptive system,Algorithm,Machine learning,Encoding specificity principle,Encoding (memory) | Journal |
Volume | Issue | ISSN |
4 | 4 | Neural Networks |
Citations | PageRank | References |
155 | 34.68 | 3 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Gail A. Carpenter | 1 | 2909 | 760.83 |
| Stephen Grossberg | 2 | 5900 | 2041.71 |
| Rosen, David B. | 3 | 823 | 111.71 |