Neural network learning of optimal Kalman prediction and control

Neural Networks

Volumn 21, Issue 9, 2008, Pages 1328-1343

  Linsker, Ralph ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

Kalman control; Kalman filter; Local cortical circuit; Recurrent neural network

Indexed keywords

CIVIL AVIATION; CONTROL SYSTEMS; CONTROL THEORY; FORECASTING; IMAGE CLASSIFICATION; LINEAR SYSTEMS; MAMMALS; NETWORK PROTOCOLS; NEURAL NETWORKS; PROBABILITY DENSITY FUNCTION; RECURRENT NEURAL NETWORKS; REINFORCEMENT LEARNING; SENSOR NETWORKS;

AS SYSTEMS; BIOLOGICAL FUNCTIONS; CIRCUIT ARCHITECTURES; CONSISTENT; CONTROL SIGNALS; CORE FUNCTIONS; CORTICAL PROCESSING; CURRENT ABILITIES; FILTERING; KALMAN CONTROL; KALMAN FILTER; KALMAN PREDICTIONS; LOCAL CORTICAL CIRCUIT; MAMMALIAN CEREBRAL CORTICES; NEURAL NETWORK LEARNINGS; NEURAL-NETWORK; NN ALGORITHMS; NOISY MEASUREMENT DATUM; NONLINEAR EXTENSIONS; OPTIMAL CONTROLS; OPTIMAL ESTIMATIONS; SENSORY; SENSORY DATUM; SIGNAL FLOWS;

IDENTIFICATION (CONTROL SYSTEMS);

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; BRAIN CORTEX; CALCULATION; LEARNING; MATHEMATICAL ANALYSIS; PREDICTION; PRIORITY JOURNAL;

ALGORITHMS; ANIMALS; ARTIFICIAL INTELLIGENCE; CEREBRAL CORTEX; FORECASTING; LINEAR MODELS; MODELS, STATISTICAL; NERVE NET; NEURAL NETWORKS (COMPUTER);

EID: 54449089010     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2008.05.002     Document Type: Article

References (37)

1. Becker S., and Hinton G.E. Self-organizing neural network that discovers surfaces in random-dot stereograms. Nature 355 (1992) 161-163
2. Callaway E.M. Local circuits in primary visual cortex of the macaque monkey. Annual Review of Neuroscience 21 (1998) 47-74
3. Douglas R.J., and Martin K.A.C. Neuronal circuits of the neocortex. Annual Review of Neuroscience 27 (2004) 419-451
4. George, D., & Hawkins, J. (2005). A hierarchical Bayesian model of invariant pattern recognition in the visual cortex. In Proceedings of the International Joint Conference on Neural Networks (pp. 1812-1817). Vol. 3
5. Gilbert C.D. Microcircuitry of the visual cortex. Annual Review of Neuroscience 6 (1983) 217-247
6. Grossberg S., and Williamson J.R. A neural model of how horizontal and interlaminar connections of visual cortex develop into adult circuits that carry out perceptual grouping and learning. Cerebral Cortex 11 (2001) 37-58
7. Haykin S. Neural networks: A comprehensive foundation. 2nd ed. (1999), Prentice Hall
8. Haykin S. Kalman filtering and neural networks (2001), Wiley-Interscience See especially chap. 2, pp. 23-68 by Puskorius, G.V. & Feldkamp, L.A. Parameter-based Kalman filter training: Theory and implementation
9. Hertz J., Krogh A., and Palmer R.G. Introduction to the theory of neural computation (1991), Addison-Wesley
10. Hinton G.E., and Ghahramani Z. Generative models for discovering sparse distributed representations. Philosophical Transactions of the Royal Society of London, B 352 (1997) 1177-1190
11. Hinton G.E., Osindero S., and Teh Y. A fast learning algorithm for deep belief nets. Neural Computation 18 (2006) 1527-1554
12. Hirsch J.A., Gallagher C.A., Alonso J.-M., and Martinez L.M. Ascending projections of simple and complex cells in layer 6 of the cat striate cortex. Journal of Neuroscience 18 (1998) 8086-8094
13. Kalman R.E. A new approach to linear filtering and prediction problems. Transactions of the ASME-Journal of Basic Engineering (Series D) 82 (1960) 35-45
14. Klimasauskas, C. C., & Guiver, J. P. (2001). Hybrid linear - Neural network process control. US Patent #6278962
15. Körding K.P., and Wolpert D.M. Bayesian integration in sensorimotor learning. Nature 427 (2004) 244-247
16. Lee T.S., and Mumford D. Hierarchical Bayesian inference in the visual cortex. Journal of the Optical Society of America A 20 (2003) 1434-1448
17. Lewicki M.S., and Sejnowski T.J. Bayesian unsupervised learning of higher order structure. Advances in Neural Information Processing Systems 9 (1997) 529-535
18. Linsker R. Local synaptic learning rules suffice to maximize mutual information in a linear network. Neural Computation 4 (1992) 691-702
19. Linsker R. Improved local learning rule for information maximization and related applications. Neural Networks 18 (2005) 261-265
20. Mountcastle V.B. Perceptual neuroscience: The cerebral cortex (1998), Harvard Univ. Press
21. Murata N., Müller K.-R., Ziehe A., and Amari S.-i. Adaptive on-line learning in changing environments. Advances in Neural Information Processing Systems 9 (1997) 599-605
22. Poggio T., and Bizzi E. Generalization in vision and motor control. Nature 431 (2004) 768-774
23. Raizada R.D.S., and Grossberg S. Context-sensitive binding by the laminar circuits of V1 and V2: A unified model of perceptual grouping, attention, and orientation contrast. Visual Cognition 8 (2001) 431-466 see refs. cited in Table 1
24. Rao R.P.N. An optimal estimation approach to visual perception and learning. Vision Research 39 (1999) 1963-1989
25. Rao R.P.N. Bayesian computation in recurrent neural circuits. Neural Computation 16 (2004) 1-38
26. Rao R.P.N. Bayesian inference and attentional modulation in the visual cortex. NeuroReport 16 (2005) 1843-1848
27. Rao R.P.N., and Ballard D.H. Dynamic model of visual recognition predicts neural response properties in the visual cortex. Neural Computation 9 (1997) 721-763
28. Rieke F., Warland D., de Ruyter van Steveninck R., and Bialek W. Spikes: Exploring the neural code (1999), MIT Press
29. Rivals I., and Personnaz L. A recursive algorithm based on the extended Kalman filter for the training of feedforward neural models. Neurocomputing 20 (1998) 279-294
30. Singhal S., and Wu L. Training multilayer perceptrons with the extended Kalman algorithm. Advances in Neural Information Processing Systems 1 (1989) 133-140
31. Szirtes G., Póczos B., and Lo{double acute}rincz A. Neural Kalman-filter. Neurocomputing 65-66 (2005) 349-355
32. Szita I., and Lo{double acute}rincz A. Kalman filter control embedded into the reinforcement learning framework. Neural Computation 16 (2004) 491-499
33. Todorov E. Stochastic optimal control and estimation methods adapted to the noise characteristics of the sensorimotor system. Neural Computation 17 (2005) 1084-1108
34. Tresp, V. (2001). Method and arrangement for the neural modelling of a dynamic system with non-linear stochastic behavior. US Patent #6272480
35. Williams, R. J. (1992). Training recurrent networks using the extended Kalman filter. In Proceedings of the International Joint Conference on Neural Networks(pp. 241-246). Vol. IV
36. Yu A.J., and Dayan P. Inference, attention, and decision in a Bayesian neural architecture. Advances in Neural Information Processing Systems 17 (2005) 1577-1584
37. Zemel R.S., Huys Q.J.M., Natarajan R., and Dayan P. Probabilistic computation in spiking populations. Advances in Neural Information Processing Systems 17 (2005) 1609-1616