Search All of the Math Forum:
Views expressed in these public forums are not endorsed by
Drexel University or The Math Forum.
|
|
|
|
Re: neural network
Posted:
Mar 14, 2013 12:46 PM
|
|
"srishti" wrote in message <khpvr7$qiu$1@newscl01ah.mathworks.com>...
> Thanks for your help. But can you please tell me how to do that?
Initialize the rng only once in the program before
1. Data division
2. Weight initialization
You don't have to know exactly where these occur. Just initialize the
RNG at the beginning of the program.
See
help rng
doc rng
Hope this helps.
Greg
P.S. Data division and Weight intialization are performed at different points
in different NNTBX versions.
1. In very old versions random weights are automatically assigned at net creation.
However, you have to do the data division yourself.
net = newff( minmax(x), [H O] );
2. In the latest obsolete version, (obsoleted in R2010b NNET 7.0), NEWFF and
special forms (NEWFIT for regregession & curvefitting ; NEWPR for classification
& pattern recognition) BOTH weight initialization and data division are automatically
performed at net creation:
net = newpr( x, t, H );
help newpr
doc newpr
3. In the current version, special forms of FEEDFORWARDNET(FITNET & PATTERNNET)
can be used. However, NEITHER initial weight initialization NOR data division are automatically performed at net creation. By default BOTH automatically occur at the FIRST call of TRAIN. However,
a. If you are looping over multiple candidate designs, weights will not reinitialize at subsequent calls of TRAIN. Therefore, it is best to explicitly initialize weights using CONFIGURE before calling TRAIN. Unless, for some reason, you want to continue the same design.
b. I don't think that subsequent calls of TRAIN in a loop will automatically redivide the data. Although this is not critical when searching for well performing weight confiurations, I will check and reply if I am wrong.
|
|
|
|
