A solution for missing data in recurrent neural networks with an application to blood glucose prediction

Advances in Neural Information Processing Systems

Volumn , Issue , 1998, Pages 971-977

  Tresp, Volker ^a   Briegel, Thomas ^a  

^a SIEMENS AG   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

BLOOD; NONLINEAR DYNAMICAL SYSTEMS; RECURRENT NEURAL NETWORKS;

BLOOD GLUCOSE MEASUREMENTS; COMPLEX INTEGRALS; FORWARD-BACKWARD KALMAN FILTERS; FREE-RUNNING MODE; MAXIMUM LIKELIHOOD LEARNING; NEURAL NETWORK MODEL; PREDICTIVE MODELING; REAL-TIME RECURRENT LEARNING;

FORECASTING;

EID: 84898996981     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. Jazwinski, A. H. (1970) Stochastic Processes and Filtering Theory, Academic Press, N.Y.
2. Lewis, F. L. (1986) Optimal Estimation, John Wiley, N.Y.
3. Shumway, R. H. and Stoffer, D. S. (1981) Time Series Smoothing and Forecasting Using the EM Algorithm, Technical Report No. 27, Division of Statistics, UC Davis.
4. Tresp, V., Moody, J. and Delong, W.-R. (1994) Neural Modeling of Physiological Processes, in Comput. Learning Theory and Natural Learning Sys. 2, S. Hanson et al, eds., MIT Press.