Classification of behavior using unsupervised temporal neural networks

Conference · Sun Mar 01 04:00:00 EST 1998

OSTI ID:645492

Adair, K L ^[1]; Argo, P ^[2]

---

1. Florida State Univ., Tallahassee, FL (United States). Dept. of Computer Science
2. Los Alamos National Lab., NM (United States)

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 with the unsupervised learning technique Adaptive Resonance Theory, Fuzzy ART. 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.

• Research Organization: Los Alamos National Lab., NM (United States)
• Sponsoring Organization: USDOE, Washington, DC (United States)
• DOE Contract Number: W-7405-ENG-36
• OSTI ID: 645492
• Report Number(s): LA-UR--97-4802; CONF-971068--; ON: DE98004362
• Country of Publication: United States
• Language: English

Related Subjects

05 NUCLEAR FUELS
99 GENERAL AND MISCELLANEOUS
LEARNING
NEURAL NETWORKS
NUCLEAR FACILITIES
ON-LINE MEASUREMENT SYSTEMS
SECURITY
TIME DEPENDENCE