Hebbian feedback covariance learning control

[Chi-Sang Poon]

The following paper is available for viewing/downloading (as PDF file) from
the IEEE electronic archive:

http://ieeexplore.ieee.org/lpdocs/epic03/RecentIssues.htm?punumber=3477

OR  http://ieeexplore.ieee.org/iel5/3477/19768/00915341.pdf


--------------------------------------------------------------------
A Hebbian Feedback Covariance Learning Paradigm for Self-Tuning Optimal
Control
D.L. Young and C.-S. Poon
IEEE Trans. Systems, Man and Cybernetics, Part B, Volume: 31 Issue: 2, pp.
173-186, April 2001

We propose a novel adaptive optimal control paradigm inspired by Hebbian
covariance synaptic adaptation, a preeminent model of learning and memory
and other malleable functions in the brain. The adaptation is driven by the
spontaneous fluctuations in the system input and output, the covariance of
which provides useful information about the changes in the system behavior.
The control structure represents a novel form of associative reinforcement
learning in which the reinforcement signal is implicitly given by the
covariance of the input-output signals. Theoretical foundations for the
paradigm are derived using Lyapunov theory and are verified by means of
computer simulations. The learning algorithm is applicable to a general
class of non-linear adaptive control problems. This on-line direct adaptive
control method benefits from a computationally straightforward design, proof
of convergence, no need for complete system identification, robustness to
noise and uncertainties, and the ability to optimize a general performance
criterion in terms of system states and control signals. These attractive
properties of Hebbian feedback covariance learning control lend themselves
to future investigations into the computational functions of synaptic
plasticity in biological neurons.