[Eeglablist] Query
Arnaud Delorme
arno at ucsd.edu
Mon Oct 8 09:29:52 PDT 2018
Hi Hamad,
I meant: "However for the inverse weight matrix, the rows are electrodes and the columns are components." Sorry for the confusion,
Arno
> On Oct 7, 2018, at 2:43 PM, Arnaud Delorme <arno at ucsd.edu> wrote:
>
> Dear Hamad,
>
>> 1) My question is that in weight matrix (after running ICA) what are the rows and what are the column values.
>
> The rows are components. The columns are electrodes.
>
> However for the inverse weight matrix, the rows are components and the columns are electrodes.
>
>> 2) I went on your website and I read ''S=WX'', and X is the EEG data etc. in terms of S,W,X what is the relation of those three matrices we obtain after RUN ICA. Can we say W= weight matrix?
>
> Yes, W is the weight matrix. Alwought in general, W = weight * sphere. Sphering is a just preprocessing before ICA. It should not have been separated from the weight matrix (but it has).
> Hope this clarifies things a bit,
>
> Arno
>
>> S=ICAsphere, ICAwinv=W inverse.
>> so out of these matrices is anyone is X? or we will have to compute.
>> I am basically confused in THE weight matrix after RUN ICA we obtain and have no labels on rows and columns. So i want to ask what are these values (rows) from left to right electrodes or components? or column value are electrodes? or both not?
>>
>>
>> Thank you for your time.
>>
>> Regards,
>> Hamad Javaid.
>> _______________________________________________
>> Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
>> To unsubscribe, send an empty email to eeglablist-unsubscribe at sccn.ucsd.edu
>> For digest mode, send an email with the subject "set digest mime" to eeglablist-request at sccn.ucsd.edu
>
> _______________________________________________
> Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
> To unsubscribe, send an empty email to eeglablist-unsubscribe at sccn.ucsd.edu
> For digest mode, send an email with the subject "set digest mime" to eeglablist-request at sccn.ucsd.edu
More information about the eeglablist
mailing list