Skip to main content
Alex R.'s user avatar
Alex R.'s user avatar
Alex R.'s user avatar
Alex R.
  • Member for 9 years, 7 months
  • Last seen more than 1 year ago
95 votes

What should I do when my neural network doesn't learn?

43 votes
Accepted

If I generate a random symmetric matrix, what's the chance it is positive definite?

38 votes

Does the normal distribution converge to a uniform distribution when the standard deviation grows to infinity?

33 votes

Does the reciprocal of a probability represent anything?

29 votes

What can one conclude about the data when arithmetic mean is very close to geometric mean?

23 votes
Accepted

Why did statisticians define random matrices?

18 votes

Why is it so important to have principled and mathematical theories for Machine Learning?

16 votes
Accepted

When the Central Limit Theorem and the Law of Large Numbers disagree

16 votes

Iconic (toy) models of neural networks

13 votes
Accepted

If we primarily use LSTMs over RNNs to solve the vanishing gradient problem, why can't we just use ReLUs/leaky ReLUs with RNNs instead?

12 votes

Why are symmetric positive definite (SPD) matrices so important?

12 votes

Why are my steps getting smaller when using fixed step size in gradient descent?

11 votes
Accepted

How can I quickly detect cheating variables in large data?

11 votes

When is t-SNE misleading?

10 votes

the turning point test

10 votes
Accepted

What does it mean for a moment generating function to exist in a neighborhood of 0?

9 votes

How does cosine similarity change after a linear transformation?

9 votes
Accepted

How to get the confidence interval of a Bernoulli trial if $\hat{p} = 0$?

9 votes
Accepted

How can we prove that a normalized kernel is also a kernel?

9 votes
Accepted

Residual network: why is each block learning residual error with respect to identity mapping?

9 votes

Why do neural networks need feature selection / engineering?

8 votes

What's the intuition of variance, quadratic variation and total variation of Brownian Motion in practice?

8 votes

Central Limit Theorem for Markov Chains

8 votes
Accepted

Using the central limit theorem

8 votes

comparison of SGD and ALS in collaborative filtering

8 votes

Value of $\mathbb{E}(\frac{1}{aX+b})$?

8 votes

How do you calculate expected value in this game of Heads or Tails?

7 votes

Use of Metropolis & Rejection & Inverse Transform sampling methods

7 votes

Why the default matrix norm is spectral norm and not Frobenius norm?

7 votes

What are the advantages of an exponential random generator using the method of Ahrens and Dieter (1972) rather than by inverse transform?

1
2 3 4 5
11