Skip to main content
mhdadk's user avatar
mhdadk's user avatar
mhdadk's user avatar
mhdadk
  • Member for 3 years, 8 months
  • Last seen this week
19 votes

Training a neural network for regression always predicts the mean

16 votes

What is the algebra showing the logistic and log loss to be equivalent?

14 votes
Accepted

Sample correlation is also a MLE estimator

14 votes
Accepted

How can I derive the EM algorithm for a mixture of two Bernoulli distributions?

13 votes
Accepted

Why does torchvision.models.resnet18 not use softmax?

10 votes
Accepted

One class classifier vs binary classifier

10 votes

Eigenvalues/Eigenvectors of Correlation and Covariance matrices

9 votes
Accepted

What assumptions about probability do different models make?

8 votes

Maximum Likelihood for Normal Distribution with Unknown Variance - Gradient Descent not working

8 votes
Accepted

Does the entropy of a random variable change under a linear transformation?

8 votes
Accepted

What is an "ERM rule" in Understanding Machine Learning by Shalev-Shwartz and Ben-David?

8 votes

Area under the ROC curve when there is imbalance: is there a problem, and if not, why does this rumor exist?

7 votes
Accepted

Covariance matrix square root

7 votes

Is the variance of the mean of a set of independent random variables equal to the average of their respective variances?

6 votes

Why is least squared loss sometimes written multiplied by $\frac{1}{2}$?

5 votes

Why use MSE instead of SSE as cost function in linear regression?

5 votes
Accepted

When are Random Variables easier to use than Sample Spaces?

5 votes
Accepted

What is the fourth moment of a Euclidean Norm?

5 votes

Why can the method of moments be expressed as a minimization problem?

4 votes

Divergence of $e_{i+1}\leftarrow e_i - x_i e_i$ for Cauchy $x_i$

4 votes

Do the states of a Random Variable have to be Mutually Exclusive?

4 votes
Accepted

How do i calculate the gradients for the bayes-by-backprop algorithm in R?

4 votes
Accepted

Can I use the mse loss function along with a sigmoid activation in my VAE?

4 votes
Accepted

What concept comes before VAE and after GMM?

4 votes
Accepted

What is the intuition behind the expected value in orginal GAN papers objective function?

4 votes

Relationship between Bayes Rule and Bayesian Networks

4 votes
Accepted

Gradient descent and Backpropagation

3 votes

Adjusting round-off error so as to have percentages that sum up to $100$

3 votes

Easy Stats Question: Sampling a bag of 457 marbles,

3 votes

Equation of Hyperplane vs Hypothesis function