Next: ReST model
Up: Multi-population recurrent model
Previous: Activation dynamics
We extend here the activation dynamics to a generic on-line
learning dynamics. A first article [10] presented a Hebbian
learning process in a non-structured RRNN,
that was found to reduce the complexity of the
dynamics (later on called ``dynamics reduction''). We propose here
a local Hebbian learning rule that relies on an on-line
estimate of the covariance between afferent and efferent signals,
as in [31].
We will suppose hereafter that we have
at each time step local estimates of mean activation, which are
stored in vector
, and updated according to
,
and we take
in our simulations.
The learning dynamics is thus described by the set of
equations:
 |
(2) |
where
is a function that prevents
weight drift when the post-synaptic neuron is saturated, and
is the learning parameter from population
towards population
(supposed small).
Note that we take into
account the discrete time delay between pre-synaptic neuron
and post-synaptic neuron
, which is important for learning
temporal dependencies [19].
Next: ReST model
Up: Multi-population recurrent model
Previous: Activation dynamics
Dauce Emmanuel
2003-04-08