Information Technology Reference
In-Depth Information
k
k
k
(
CV
(
CV
DV
) * (1
AL
)) *
p
4
im
,
1
jm
,
1
jm
,
1
im
,
1
k
k
CV
CV
(11)
im
,
im
,
1
z
k
k
k
(
CV
(
CV
DV
) * (1
AL
)) *
p
4
jm
,
1
im
,
1
im
,
1
jm
,
1
k
k
CV
CV
(12)
jm
,
jm
,
1
z
Owing to interactions, the characteristics of the vector of differences (DV) of module i
at
iteration m are also changed as follows :
k
k
k
k
DV
p
5*(
CV
IV
)
(1
p
5)
DV
,
p5<1
(13)
im
,
im
,
im
,
im
,
1
it is possible to say that CV is the long-term memory of a module and DV is its short-term
memory.
The modules with AL exceeding a threshold ( p8 in this model or p5 in the previous one) ,
also, influence the position of the center of perceptive spot. This position (center position or
CP) is determined at iteration m as follows:
iz
CP
CP
p
10 *
(
T
CP
)
mm
1
i mm
,
1
i
1
and
i
Ti
/
z
if
AL
p
8
, otherwise
T
P
.
(14)
,
im
,
im
,
m
1
It is suggested the position of the left boundary of the system is 0 and that of the right
boundary is 1.
As is emphasized above, only the modules, which are within perceptive spot, are filled by
information from the environment, i.e. if |CP
m
-i/z| ≤ p11, then for module i at iteration
m+1
k
k
IV
E
noise
im
,
1
m
and for modules which do not meet this inequality
(15)
im
IV
noise
.
,
1
The formulae for computing activation level (AL), output vector OV, and the environment
are identical those in model 1.
An idea underlying the usage of model is that under certain circumstances the input vectors
of modules i.e. the state of the environment and the vectors of coefficients in the system
ought to converge to each other. The results of a simulation intended to test this assumption
are presented in table 2. In this simulation as well as in the simulations below, the number of
modules in the system (z) was 300 and the vectors in each module were three-dimensional.
The constants of environment vector in this simulation were 10, 50, and 90, accordingly.
Perceptive spot covered all modules, and each module was able to interact with all of the
rest i.e. p2 and p11 were 0,95. The threshold for interactions (p3) was 4,2. The other
parameters are in Appendix, they were kept invariable through the other simulations. The
values averaged across the components of input vectors were used as the description of the
