Discover MakerZone

MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi

Learn more

Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply Today

Thread Subject:
How to list neural net input/output processing options ?

Subject: How to list neural net input/output processing options ?

From: Greg Heath

Date: 23 Dec, 2012 22:35:08

Message: 1 of 4

[x,t] = simplefit_dataset;
net = newff(x,t,4);

  1. Using either net.inputs{:} or net.inputs{:,:}, I get the list
  
 ans =

    Neural Network Input

              name: 'Input'
    feedbackOutput: []
       processFcns: {'fixunknowns', removeconstantrows,
                    mapminmax}
     processParams: {1x3 cell array of 2 params}
   processSettings: {1x3 cell array of 3 settings}
    processedRange: [1x2 double]
     processedSize: 1
             range: [1x2 double]
              size: 1
          userdata: (your custom info)
          
2. How do I list ONLY net.inputs.processFcns? I am only getting the first
component from net.inputs.processFcns{ : }, net.inputs.processFcns{ :, : },
net.inputs.processFcns{ 1, : } and net.inputs.processFcns{ 1,1:end }.

TIA

Greg

Subject: How to list neural net input/output processing options ?

From: Luca I

Date: 24 Dec, 2012 08:55:12

Message: 2 of 4

"Greg Heath" <heath@alumni.brown.edu> wrote in message <kb80us$72p$1@newscl01ah.mathworks.com>...
> [x,t] = simplefit_dataset;
> net = newff(x,t,4);
>
> 1. Using either net.inputs{:} or net.inputs{:,:}, I get the list
>
> ans =
>
> Neural Network Input
>
> name: 'Input'
> feedbackOutput: []
> processFcns: {'fixunknowns', removeconstantrows,
> mapminmax}
> processParams: {1x3 cell array of 2 params}
> processSettings: {1x3 cell array of 3 settings}
> processedRange: [1x2 double]
> processedSize: 1
> range: [1x2 double]
> size: 1
> userdata: (your custom info)
>
> 2. How do I list ONLY net.inputs.processFcns? I am only getting the first
> component from net.inputs.processFcns{ : }, net.inputs.processFcns{ :, : },
> net.inputs.processFcns{ 1, : } and net.inputs.processFcns{ 1,1:end }.
>
> TIA
>
> Greg

__________________________________________________________-

I suppose that you must write:

net.inputs{1}processFcns to obtain something like:

ans=

'fixunknowns' 'removeconstantrows' 'mapminmax'

and to overwrite these functions you must write:

net.inputs{1}.processFcns = {'removeconstantrows' 'mapminmax'};

I hope I've understand what you need...

Subject: How to list neural net input/output processing options ?

From: Greg Heath

Date: 24 Dec, 2012 20:41:15

Message: 3 of 4

"Luca I" <luca_iannone@hotmail.com> wrote in message <kb959g$141$1@newscl01ah.mathworks.com>...
> "Greg Heath" <heath@alumni.brown.edu> wrote in message <kb80us$72p$1@newscl01ah.mathworks.com>...
> > [x,t] = simplefit_dataset;
> > net = newff(x,t,4);
> >
> > 1. Using either net.inputs{:} or net.inputs{:,:}, I get the list
> >
> > ans =
> >
> > Neural Network Input
> >
> > name: 'Input'
> > feedbackOutput: []
> > processFcns: {'fixunknowns', removeconstantrows,
> > mapminmax}
> > processParams: {1x3 cell array of 2 params}
> > processSettings: {1x3 cell array of 3 settings}
> > processedRange: [1x2 double]
> > processedSize: 1
> > range: [1x2 double]
> > size: 1
> > userdata: (your custom info)
> >
> > 2. How do I list ONLY net.inputs.processFcns? I am only getting the first
> > component from net.inputs.processFcns{ : }, net.inputs.processFcns{ :, : },
> > net.inputs.processFcns{ 1, : } and net.inputs.processFcns{ 1,1:end }.
> >
> > TIA
> >
> > Greg
>
> __________________________________________________________-
>
> I suppose that you must write:
>
> net.inputs{1}processFcns to obtain something like:
>
> ans=
>
> 'fixunknowns' 'removeconstantrows' 'mapminmax'
>
> and to overwrite these functions you must write:
>
> net.inputs{1}.processFcns = {'removeconstantrows' 'mapminmax'};
>
> I hope I've understand what you need...

Perfectly. Tanks.

Greg

Subject: How to list neural net input/output processing options ?

From: Greg Heath

Date: 24 Dec, 2012 20:47:14

Message: 4 of 4

"Luca I" <luca_iannone@hotmail.com> wrote in message <kb959g$141$1@newscl01ah.mathworks.com>...
> "Greg Heath" <heath@alumni.brown.edu> wrote in message <kb80us$72p$1@newscl01ah.mathworks.com>...
> > [x,t] = simplefit_dataset;
> > net = newff(x,t,4);
> >
> > 1. Using either net.inputs{:} or net.inputs{:,:}, I get the list
> >
> > ans =
> >
> > Neural Network Input
> >
> > name: 'Input'
> > feedbackOutput: []
> > processFcns: {'fixunknowns', removeconstantrows,
> > mapminmax}
> > processParams: {1x3 cell array of 2 params}
> > processSettings: {1x3 cell array of 3 settings}
> > processedRange: [1x2 double]
> > processedSize: 1
> > range: [1x2 double]
> > size: 1
> > userdata: (your custom info)
> >
> > 2. How do I list ONLY net.inputs.processFcns? I am only getting the first
> > component from net.inputs.processFcns{ : }, net.inputs.processFcns{ :, : },
> > net.inputs.processFcns{ 1, : } and net.inputs.processFcns{ 1,1:end }.
> >
> > TIA
> >
> > Greg
>
> __________________________________________________________-
>
> I suppose that you must write:
>
> net.inputs{1}processFcns to obtain something like:
>
> ans=
>
> 'fixunknowns' 'removeconstantrows' 'mapminmax'
>
> and to overwrite these functions you must write:
>
> net.inputs{1}.processFcns = {'removeconstantrows' 'mapminmax'};
>
> I hope I've understand what you need...

Yes. Thanks.

However, I don't understand why the {1} is needed. For 99.9% of problems there is only one input.

Greg

Tags for this Thread

No tags are associated with this thread.

What are tags?

A tag is like a keyword or category label associated with each thread. Tags make it easier for you to find threads of interest.

Anyone can tag a thread. Tags are public and visible to everyone.

Contact us