We call ``spontaneous dynamics'' the dynamics corresponding to
Eq.(1), when the weights have been defined according to
a random draw (there is no learning).
As we use rather large systems, the behavior of a given
system is supposed to be representative of the
behavior of a whole family of random systems that
have been defined according to the same parameters set. This
assumption is only exact at the limit of large sizes [25].
At finite size, we have checked the reproducibility and genericity
of the behaviors described hereafter on several networks.
Table 1:
Few parameters are necessary to define the initial
system. The thresholds and are set
strong enough to lower activity and avoid saturation. The
feedforward links and inner links are randomly set according to
and
(the feedforward
links are adapted to the statistics of the input signals, where
corresponds to the mean sparsity of the input signal).
Initially (before training), feedback links are equal to zero, so
that the secondary layer activity has no influence on the primary
layer. Lateral links on primary layer are also equal to zero. Gain
parameter allows for a chaotic dynamics in the secondary
layer. Typical learning parameters are also given in the right
part of the table (see text).
Parameters for the 2-layers ReST
model
Typical learning parameters
Thresholds
Weights standard
deviation
Gain
Weight adaptation
Update
rate of
the mean activation
The mean field equations [6] have helped us to
determine the parameters of the system (the parameters are
displayed in Tab.1). The parameters have been chosen
for the inner dynamics to be chaotic, so that the response of the
system is not fully specified by the input sequence. More
precisely, taking into account the sparsity of the input signal,
the value of
is chosen such that the
feed-forward local field mean standard deviation
. With setting
, the mean field equations allow to predict
that
at the thermodynamic limit, so that inner signal amplitude is
significantly stronger than feed-forward signal amplitude.
At a given time , the spatial pattern of activation
is such that 15% to 20% of the neurons are
active, i.e. have their activation
(
at the thermodynamic limit).
One can also note that
almost every neuron is dynamically active in secondary layer, i.e.
80% of the neurons have an activation signal
whose standard deviation is
.
Next:Predictability Up:ReST model Previous:A 2-layers perceptual model
Dauce Emmanuel
2003-04-08