Arno Veletanlic
Arno Veletanlic
Hi again, Thanks for the detailed answer. My original question concerning point 1 could be updated as follows: why is the embedding network/ embedding layer better framed as Conv1D's and...
Hi, Would it be possible to have some kind of update? Thanks!
Hi again, I'm reading the NCC code more carefully now, and I noticed something odd. You made the choice to use ```python criterion = th.nn.BCEWithLogitsLoss() ``` and therefore your network...
Thanks, Additionally, I've been doing some experiments and it seems that learning FCM structure from clouds of points is highly nontrivial, as depending on the FCM, It occurred very often...
The papers says that if `integral of slope y=f(x) < 0` predict X->Y. If you want to keep your convention (`+` for XY, `-` for YX), you should return `b-a`,...
Hi, Would it be possible to have some kind of update? Thanks!
Hi, I checked the official website in details, It highly likely that the current CDT TCEP version is simply the current TCEP (with 108 pairs) with the multivariate one removed....
As a reference: ```python 0.166, 0.166, 0.167, 0.166, 0.143, 0.143, 0.143, 0.143, 0.143, 0.143, 0.142, 0.5, 0.25, 0.25, 0.25, 0.25, 0.5, 1, 1, 0.166, 0.167, 0.333, 0.333, 0.334, 0.125, 0.125,...
**edit:** Most missing pair have a corresponding weight of 0.
For future reference: this test essentially compares the test statistics ```m*HSIC_b```, it is called in this way not because the Gamma approximation is used, but because the gamma approximation is...