Next: DefaultUndefs.m
Up: Base Modules
Previous: Base Modules
ProbSpec.m
Network definition file. Will be run as a module to start training on the specified
network. Since it is contained in a problem subdirectory (see Section 1.3
for more on directory hierarchy), the first thing it does is to add the Base/
and Tools/ directories to the default search path in the environment.
The remaining file consists of variable declarations, and ends with a call to
the training module (see Sections 3.1 for definition and 4.1.5
for details). The variables at the time of writing this manual are as follows:
- inputfilename
- The name of the input file for
the problem, as defined in Section 2.
- outputfilename
- The name of the output file
for the problem, as defined in Section 2.
- nOfSamples
- The number of patterns (samples) in
the data set (see Section 6 for possible amendments).
- numInputs
- Number of units in the input layer of
the network. This value should be consistent with the patterns in the data set
(see Section 6 for possible amendments).
- numHids
- Number of units in the hidden layer of the
network. This value is independent of the data set, although should be chosen
with care to minimize training time[Reed98, pp. 68, 69].
- numOuts
- Number of units in the output layer of the
network. This value should be consistent with the patterns in the data set (see
Section 6 for possible amendments).
- weightLim
-
limit for the weight initialization
procedure. See the file Base/RndWtsBs.m for interpretation of values
(see Section 4.1.4 for implementation).
- rate
- Learning rate parameter for the back-propagation
algorithm. This value is independent of the data set, although should be chosen
with care to minimize training time[Reed98, pp. 68, 69], [Hassoun95, pp. 211-213].
- epochs
- Maximum number of epochs that the network will
be allowed to train. Once this limit is reached before meeting the convergence
criterion, it will be deemed failure to converge (see Section 3.1.2).
- pSS
- Once as many epochs to display the state of the network.
Useful for keeping the information output limited, against obscurity. Also affects
the plot step size while plotting results of errors (see Section 3.1.3.1).
- checkType
- Convergence check procedure explained
in Section 3.1.2.1. For the possible values, see Section 4.1.10.
- back-propagation
- If it is 1 use back-propagation,
otherwise calculate only feed-forward results without employing a learning procedure.
Implementation given in weight update rules (see Section 4.1.9).
- unitType
- Activation function to be used in all units
of the network. Possible values are `val' and `sig' ,
see the file Base/MainLoop.m (see Section 4.1.5) for
the usage of this variable.
- trainType
- Training style, either 'incremental'
or 'batch' update of the weights of the network. See
the file Base/MainLoop.m for interpretation of values (see Section
4.1.5).
- trainMethod
- Training method selection. Can either
be 'Standard' for standard back-propagation
and 'Newton' for pseudo-Newton (approximate
Newton) weight update rule [Hassoun95, pp. 215-216]. See the file Base/MainLoop.m
for interpretation of values (see Section 4.1.5).
- patternRandomization
- Boolean variable
which decides whether to shuffle order of patterns in an epoch. Useful in incremental
learning style. See the file Base/MainLoop.m for interpretation of
values (see Section 4.1.5).
- criterion , missesCriterion , rejectionCriterion
- criterion
values that will be used for the convergence check procedure (see Section 3.1.2.1).
See the file Base/ConvChk.m for interpretation of values (see Section
4.1.10).
- continue
- Boolean value to determine whether to reuse
previous weights. Useful when continuing from intentionally stopped training
sessions. If this value is set to 1, the network will continue learning from
where it left last time, otherwise the weights will be initialized to random
values.
- muNewton
- A special training parameter only for the
Pseudo-Newton rule, if it is chosen as trainMethod. It is for avoiding
infinite slopes in derivative calculations. Implementation given in weight update
rules (see file Base/batchModeNewton.m and Base/incrementalModeNewton.m
explained in Section 4.1.9) [Hassoun95, pp. 215-216].
- normalizeInputs , normalizeWeights
- Boolean
variables for activating normalizing procedures. These procedures are devised
to ease the training algorithms. For data sets which contain input values bigger
than 1, setting normalizeInputs will normalize all inputs to 1 prior
to training. For data sets with many input or hidden units, setting normalizeWeights
will divide initialized weight values to the fan-in number of the target unit
[Hassoun95, p. 242]. normalizeInputs is implemented in Base/LoadIO.m
(see Section 4.1.3) and normalizeWeights is implemented
in Base/RndWtsBs.m (see Section 4.1.4).
- randomseed
- If defined, it will be used for the
random weight values used for initialization of the network. This is useful,
if one needs to create the exact network twice, or in two different computers,
giving the same number seed value would accomplish this.
Next: DefaultUndefs.m
Up: Base Modules
Previous: Base Modules
Cengiz Gunay
2000-06-25