ABSTRACT
Within the broad scope of the study of artificial intelligence (AI), research in neural networks is characterized by a particular focus on pattern recognition and pattern generation. Many neural network methods can be viewed as generalizations of classical pattern-oriented techniques in statistics and the engineering areas of signal processing, system identification, and control theory. As in these parent disciplines, the notion of “pattern” in neural network research is essentially probabilistic and numerical. Neural network methods have had their greatest impact in problems where statistical issues dominate and where data are easily obtained.
