The NEURAL Procedure
PERTURB_Statement__Perturbs_weights._Perturbing_weights_can_sometimes_allow_you_to_escape_a_local_minimum.__Category'>PERTURB Statement
Perturbs weights. Perturbing weights can sometimes allow you to escape a local minimum.
Category Action Statement - affects the network or the data sets. Options set in an action statement
affect only that statement.
PERTURB weight-list / <
RANDF=
number >
<
OUTEST=
SAS-data-set>
<
RANDIST=
name>
<
RANDOM=
integer>
<
RANLOC=
number>
<
RANSCALE=
number>;
Required Argument
weight-list
List of weights to freeze.
Weight-list consists of 0 or more repetitions of:
wname --> wname-2 where:
wname
is the unit name, the layer ID, BIAS, or ALTITUDE
wname-2
is the unit name or layer ID
Options
RANDF=number
Specifies the degrees of freedom parameter for random numbers. See the
Randomization Options
and Default Parameters
table for values.
OUTEST=SAS-data-set
Specifies the output data set containing all the weights.
Default:
none
RANDIST=name
Specifies the type of distribution for random numbers. See the
Randomization Options and
Default Parameters
table for values.
RANDOM=integer
Specifies the random number seed.
Default:
0
RANLOC=number
Specifies the location parameter for random numbers. See the
Randomization Options and Default
Parameters
table for values.
RANSCALE=number
Specifies the scale parameter for random numbers. See the
Randomization Options and Default
Parameters
table for values.
Copyright 2000 by SAS Institute Inc., Cary, NC, USA. All rights reserved.
The NEURAL Procedure
PRELIM Statement
Performs preliminary training to reduce the risk of bad local optima.The final weights and biases
in a trained network depend on the initial values. The PRELIM statement repeatedely trains a
network for a smal number of iterations (default 20) using different initializations. The final
weights of the best trained network are then used to initialize a subsequent TRAIN statement.
Category Action Statement - affects the network or the data sets. Options set in an action statement
affect only that statement.
PRELIM integer
<
ACCELERATE=
number>
<
DECELERATE=
number>
<
INEST=
SAS-data-set>
<
LEARN=
number>
<
MAXLEARN=
number>
<
MAX | MAXMOMENTUM=
number>
<
MINLEARN=
number >
<
MOM | MOMENTUM=
number>
<
OUTEST=
SAS-data-set>
<
PREITER=
integer>
<
PRETECH=
name>
<
PRETIME=
number>
<
RANDBIAS|NORANDBIAS>
<
RANDOUT|NORANDOUT>
<
RANDOM=
integer>;
Required Argument
integer
Specifies the number of preliminary optimizations.
Options
ACCEL | ACCELERATE=number
Specifies the rate of increase of learning for the RPROP optimization technique.
Range:
number > 1
Default:
1.2
DECEL | DECELERATE=number
Specifies the rate of decrease of learning for the RPROP optimization technique.
Range:
0 < number < 1
Default:
0.5
INEST=SAS-data-set
Specifies the input data set that contains some or all weights. Any weights in the INEST= data set
that have missing values are assigned values according to the RANDOM=, RANDOUT, and
RANDBIAS options, as well as the options that pertain to random number distributions that you
specify in the Random statements.
LEARN=number
Specifies the learning rate for BPROP or the initial learning rate for QPROP and RPROP.
Range:
number > 0
Default:
0.1
MAXLEARN=number
Specifies the maximum learning rate for RPROP.
Range:
number > 0
Default:
Reciprocal of the square root of the machine epsilon
MAXMOM | MAXMOMENTUM=number
Specifies the maximum momentum for BPROP.
Range:
number > 0
Default:
1.75
MINLEARN=number
Specifies the minimum learning rate for RPROP.
Range:
number > 0
Default:
Square root of the machine epsilon
MOM | MOMENTUM=number
Specifies the momentum for BPROP.
Range:
0 number < 1
Default:
For BPROP: 0.9; for RPROP: 0.1
OUTEST=SAS-data-set
Specifies the output data set that contains all the weights.
PREITER=integer
Specifies the maximum number of iterations in each preliminary optimization.
Default:
10
PRETECH | TECHNIQUE=name
Specifies the optimization technique. See
TRAIN Statement
.
Default:
Same as TECH= in the TRAIN statement.
PRETIME=number
Specifies the amount of time after which training stops.
RANDBIAS | NORANDBIAS
Specifies whether to randomize output biases.
Default:
NORANDBIAS, which sets bias to the inverse activation function of the
target mean.
[NORANDBIAS overrides whatever you specify in the RANDOM
statement.]
RANDOM=integer
Specifies the random number seed.
Default:
0
RANDOUT | NORANDOUT
Specifies whether to randomize the output connection weights.
Default:
NORANDOUT, which sets weights to 0.
[NORANDOUT overrides whatever you specify in the RANDOM
statement.]
Copyright 2000 by SAS Institute Inc., Cary, NC, USA. All rights reserved.