I CLASSIFICATION OF BEHAVIOR USING UNSUPERVISED TEMPORAL NEURAL NETWORKS Kristin L . Adair

Adding recurrent connections to unsupervised neural networks used for clustering creates a temporal neural network which clusters a sequence of inputs as they appear over time. The model presented combines the Jordan architecture [61 with the unsupervised learning technique Adaptive Resonance Theory, FuzzyART[41. The combination yields a neural network capable of quickly clustering sequential pattern sequences as the sequences are generated. The applicability of the architecture is illustrated through a facility monitoring problem.