Prev: Importing csv file - only two (not 12) columns appear
Next: Regarding getting pixel information of cursor
From: Susana on 16 Jul 2010 05:43
Hi, thanks

Unfortunately I already had tried that, but I received this error:
"Undefined function or method 'fix2' for input arguments of type 'double'"

How don't know what I should do. Probably I'm not using correct...
What you mean with:
" This response surface can be put in the form of an objective function as required by MATLAB optimization algorithms"

I had the matrix with my data, and I also created surfaces. But I don't know how to put in a"form of an objective function" probably.... :S

thanks,
Susana



James Allison <james.allison(a)mathworks.com> wrote in message <i1nneu$hur$1(a)fred.mathworks.com>...
> You could fit a response surface (like a polynomial or neural network)
> to your data. This response surface can be put in the form of an
> objective function as required by MATLAB optimization algorithms, and
> then use an unconstrained optimization algorithm (e.g., fminunc) to find
> the minimum of this surface. The solution will approximate the minimum
> of the actual system that generated the data.
>
> If you have the ability to gather more data, you can improve the
> accuracy of the solution by resampling in a tighter region near the
> optimum of the response surface, fitting a new surface using the new
> data, and performing the optimization again on the updated surface. This
> "successive surrogate modeling" approach can be iterated with
> increasingly tight sampling regions to improve accuracy further.
>
> -James
>
> Susana wrote:
> > Hi,
> >
> > I'm working with MatLab since just 2 months and I need to do a Steepest
> > Descent in my data. The problem is that my data is not a function, but a
> > Matrix (MAT-file).
> > And all the help that I found is to functions....
> > Some idea??
> > Thanks in advance,
> >
> > Susana
From: James Allison on 21 Jul 2010 14:39
The error with "fix2" is likely a function syntax error. Working out the
syntax details is something tech support can help you with. Contact them
by going to mathworks.com and clicking: contact us > request technical
support. You will need a valid license number. You can get your license
information by typing ver at the MATLAB command line.

You can also get more information about debugging from:

http://www.mathworks.com/support/tech-notes/1200/1207.html
http://blogs.mathworks.com/loren/2010/03/19/debugging-approaches/

You can get specific information about how to create objective functions
for use with optimization from:

http://www.mathworks.com/access/helpdesk/help/toolbox/optim/ug/brhkghv-3.html

I hope this helps.

-James

Susana wrote:
> Hi, thanks
>
> Unfortunately I already had tried that, but I received this error:
> "Undefined function or method 'fix2' for input arguments of type 'double'"
>
> How don't know what I should do. Probably I'm not using correct...
> What you mean with:
> " This response surface can be put in the form of an objective function
> as required by MATLAB optimization algorithms"
>
> I had the matrix with my data, and I also created surfaces. But I don't
> know how to put in a"form of an objective function" probably.... :S
>
> thanks, Susana
>
>
>
> James Allison <james.allison(a)mathworks.com> wrote in message
> <i1nneu$hur$1(a)fred.mathworks.com>...
>> You could fit a response surface (like a polynomial or neural network)
>> to your data. This response surface can be put in the form of an
>> objective function as required by MATLAB optimization algorithms, and
>> then use an unconstrained optimization algorithm (e.g., fminunc) to
>> find the minimum of this surface. The solution will approximate the
>> minimum of the actual system that generated the data.
>>
>> If you have the ability to gather more data, you can improve the
>> accuracy of the solution by resampling in a tighter region near the
>> optimum of the response surface, fitting a new surface using the new
>> data, and performing the optimization again on the updated surface.
>> This "successive surrogate modeling" approach can be iterated with
>> increasingly tight sampling regions to improve accuracy further.
>>
>> -James
>>
>> Susana wrote:
>> > Hi,
>> > > I'm working with MatLab since just 2 months and I need to do a
>> Steepest > Descent in my data. The problem is that my data is not a
>> function, but a > Matrix (MAT-file).
>> > And all the help that I found is to functions....
>> > Some idea??
>> > Thanks in advance,
>> > > Susana
First  |  Prev  | 
Pages: 1 2
Prev: Importing csv file - only two (not 12) columns appear
Next: Regarding getting pixel information of cursor