Neural learning of Kalman filtering, Kalman control, and system identification

Authors:
Ralph Linsker
Affiliations:
IBM T. J. Watson Research Center, Yorktown Heights, NY
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 9
Cited 0

Dynamic model of visual recognition predicts neural response properties in the visual cortex

Neural Computation
Bayesian computation in recurrent neural circuits

Neural Computation
Kalman filter control embedded into the reinforcement learning framework

Neural Computation
Improved local learning rule for information maximization and related applications

Neural Networks
Stochastic Optimal Control and Estimation Methods Adapted to the Noise Characteristics of the Sensorimotor System

Neural Computation
A fast learning algorithm for deep belief nets

Neural Computation
Local synaptic learning rules suffice to maximize mutual information in a linear network

Neural Computation
Neural network learning of optimal Kalman prediction and control

Neural Networks
Neural Kalman filter

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper shows how to implement Kalman estimation (including filtering and prediction) and control, and system identification, within a neural network (NN) whose only input is a stream of noisy measurement data. The operation of the fully-integrated algorithm is illustrated by a numerical example. The resulting network is a multilayer recurrent NN that may be useful for engineering applications. The algorithm is found to impose constraints on the NN circuitry and architecture. It is of interest that the derived circuit bears certain resemblances to the putative 'local circuit' of mammalian cerebral cortex. These similarities are discussed with reference to speculations on the possible fundamental operations of cerebral cortex.