Learning, categorization, rule formation, and prediction by fuzzy neural networks

Author(s): Carpenter, G.A. | Grossberg, S. |

Year: 1996

Citation: In C.H. Chen (Ed.) Fuzzy Logic and Neural Network Handbook, New York: McGraw-Hill, 1.3-1.45.

Abstract: For many years, the subjects of artificial intelligence, neural networks, and fuzzy logic were developed by separate intellectual communities. This was due more, perhaps, to social and institutional barriers to communication than to inherently different research goals and results. One manifestation of these barriers came in the form of claims, especially from the AI community, that the other approaches could not succeed at solving certain problems, despite progress to the contrary. This divisive period is fortunately substantially behind us. A growing number of models now computationally synthesize properties of expert production systems, neural networks, and fuzzy logic. Fuzzy ARTMAP, the topic of this chapter, is one such model. Fuzzy ARTMAP is a family of self-organizing neural architectures that are capable of rapidly learning to recognize, test hypotheses about, and predict consequences of analog or binary input patterns occurring in a nonstationary time series.

Topics: Machine Learning, Applications: Remote Sensing, Models: Fuzzy ARTMAP,

PDF download

Cross References