NAME
linknets - connects two or more SNNS network files into one
single network
SYNOPSIS
linknets -innets netfile ... [ -outnets
netfile ... ] -o output-network [ options ]
DESCRIPTION
linknets allows to easily link several independent networks
to one combined network. In general n so called input networks (
n ranges from 1 to 20) are linked to m so called output
networks ( m ranges from 0 to 20). It is possible to add a new layer
of input units to feed the former input units of the input networks. It is
also possible to add a new layer of output units which is either fed by the
former output units of the output networks (if output networks are given) or
by the former output units of the input networks.
PARAMETERS
-innets netfile
the name of a network file to be the pre-processor of the
resulting network. There must be at least one innets option present. Up
to 20 networks might be given here, which then will be put next to each other
in the resulting network, i.e. the new input layer will be the union of the
input layers of these networks.
-outnets netfile
the name of a network file to be the post-processor of
the resulting network. Up to 20 networks might be given here, which then will
be put next to each other in the resulting network, i.e. the new output layer
will be the union of the output layers of these networks.
-o output-network
the filename of the network to be generated.
OPTIONS
-inunits
To use the option -inunits, all input networks
must have the same number of input units. If -inunits is given, a new
layer of input units is created. The number of new input units is equal to the
number of (former) input units of a given input network. The new input units
are connected by a one-to-one scheme to the (former) input units, which means,
that every former input unit gets input activation from exactly one new input
unit. The newly created network links are initialized with weight 1.0. The
(former) input units of the input networks are changed to be special hidden
units in the resulting network (incoming weights of special hidden units are
not changed during further training). This connection scheme is useful to feed
input patterns into several networks with similar input structure.
-inconnect n
If -inconnect n is given, n new
input units are created. These new input units are fully connected to the
(former) input units of all input networks. The (former) input units of the
input networks are changed to be hidden units in the resulting network. The
newly created network links are initialized with weight 0.0.
Note, that -inunits and -inconnect may not be used
together.
-outconnect n
If -outconnect n is given, n new
output units are created. These new output units are fully connected either to
the (former) output units of all output networks (if output networks are
given) or to the (former) output units of all input networks. The (former)
output units are changed to be hidden units in the resulting network. The
newly created network links are initialized with weight 0.0.
-direct
By default, all output units of the input networks are
fully connected to all input units of the output networks. In some cases it is
usefull, not to use a full connection but a one-to-one connection scheme. This
is performed by giving the option -direct. To use this option, the sum
of all (former) output units of the input networks must equal the sum of all
(former) input units of the output networks. Following the given succession of
input and output networks (and the network dependent succession of input and
output units), every (former) output unit of the input networks is connected
to exactly one (fomer) input unit of the output networks. The newly created
network links are initialized with weight 1.0. The (former) input units of the
output networks are changed to be special hidden units in the resulting
network (incoming weights of special hidden units are not changed during
further training). The (former) output units of the input networks are changed
to be hidden units. This connection scheme is usefull to directly feed the
output from one (or more) network(s) into one (or more) other network(s).This
option is ignored if no output networks are given.
SEE
ALSO
It is strongly recommended to examine the examples in the SNNS
user manual under the SNNS installation directory or in the hypertext manual
at
http://www-ra.informatik.uni-tuebingen.de/SNNS/UserManual/UserManual.html
snns(1) neural network simulation package SNNS
