# fabee

Tuebingen

kyb.tuebingen.mpg.de/~fabee

PhD student in computational neuroscience.
 6h comment What's the best way to test the uniformity of location data?Maybe I misunderstood his question. I though the OP was searching for a method to test whether a collection of points in $[0,1]$ is uniformly distributed. That could be checked with a KS test. But maybe "spatial" has a different meaning that I don't know. 8h comment Law of Large numbers and central limit theoremIf you want more details on the last part of @gui11aume's answer, you can check out the answer to here (stats.stackexchange.com/questions/44262/…). 12h answered What's the best way to test the uniformity of location data? 2d accepted Conditional Independence and Mutual information 2d answered Scaling hinge loss in SVM Dec 5 accepted Color whole section line in org-mode depending on tag Dec 3 comment Doubt in derivative of logarithm@Drew75 is right. Your derivative does not make sense because the $x_i$ is in front of the sum. But if you compute a log-likelihood, shouldn't it be $\frac{d}{dx}\sum_i \log p(x_i)$? Dec 3 comment Doubt in derivative of logarithmyes, it should. The best way to see it is $\frac{d}{dx}\sum_i \log x_i=\sum_i \frac{d}{dx}\log x_i=\sum_i\frac{1}{x_i}$. Dec 3 comment Confidence interval of RMSEI don't think I am wrong. Just think about it like this: The MSE is actually the sample variance since $\mbox{MSE} = \hat\sigma^2 = \frac{1}{n}\sum_{i=1}^n (x_i-\hat x_i)^2$. The only difference is that you divide by $n$ and not $n-1$ since you are not subtracting the sample mean here. The RMSE would then correspond to $\sigma$. Therefore, the population RMSE is $\sigma$ and you want a CI for that. That's what I derived. Otherwise I must completely misunderstand your problem. Dec 2 revised Confidence interval of RMSEadded 207 characters in body Dec 2 answered Confidence interval of RMSE Nov 30 comment Principal Components Analysis with ConstraintsI still do not see how the maximization problem makes sense. What does $\mbox{maximize}X\Sigma X^\top$ mean if $X\Sigma X^\top$ is a matrix? Nov 30 comment Principal Components Analysis with ConstraintsThe question as you phrased it is inconsistent: You said that $\Sigma\in \mathbb R^{n\times n}$, but $x$ is a matrix $\in R^{T\times n}$. Then $\Sigma x$ does not make sense, since $x$ should have $n$ rows. But even if you transpose it, then $x^\top \Sigma x$ would be a matrix. What does maximization mean then? Also, if $x$ is a matrix, what do the indices mean in the constraint? Nov 26 comment What class of non linear functions can be modeled by a neural networkWithout any further restrictions, the answer is: any class. That's because you could have a neuron for each function in your function class. Nov 20 comment Color whole section line in org-mode depending on tagThanks. I wait a little before accepting your answer (because of the AFAICT part). Nov 20 asked Color whole section line in org-mode depending on tag Oct 24 awarded Scholar Oct 24 comment Straight into bios after starting windows 8 on asus zenbookI was afraid of that. Ok then, that's what I am going to do. Thanks. Oct 24 accepted Straight into bios after starting windows 8 on asus zenbook Oct 24 awarded Student