User figs_and_nuts

26 votes

1 answer

31k views

What are the implications of scaling the features to xgboost?

asked Jun 27, 2018 at 18:40

19 votes

2 answers

7k views

Neural networks vs everything else

asked May 3, 2018 at 16:13

11 votes

2 answers

1k views

Why go through the trouble of expectation maximization and not use gradient descent?

asked Oct 14, 2023 at 10:56

9 votes

1 answer

3k views

Why maximizing the lower bound of variational evidence maximizes the probability of observing data

asked Nov 27, 2017 at 9:16

9 votes

2 answers

10k views

Is a policy always deterministic in reinforcement learning?

asked Dec 1, 2017 at 19:47

9 votes

1 answer

2k views

Understanding batch normalization

asked Oct 30, 2017 at 15:18

9 votes

2 answers

5k views

Explaining dimensionality reduction using SVD (without reference to PCA)

asked Apr 22, 2018 at 10:48

9 votes

2 answers

17k views

What is the output of a tf.nn.dynamic_rnn()?

asked Feb 23, 2018 at 12:04

8 votes

1 answer

562 views

Why is rejection of null hypothesis not a case of prosecutor's fallacy?

asked Sep 12, 2019 at 18:55

7 votes

1 answer

3k views

Understanding semi supervised technique called mean teachers

asked Mar 10, 2019 at 17:15

6 votes

2 answers

3k views

Does a Binomial converge to Poisson or Normal?

asked Apr 10, 2021 at 11:57

6 votes

3 answers

1k views

why can two random variables be added only when they have the same domain?

asked Sep 29, 2019 at 5:03

4 votes

1 answer

3k views

Understanding regularization in xgboost

asked Jun 18, 2018 at 6:12

4 votes

2 answers

3k views

If z is uniform normal is $f(z;\theta)$ a normal distribution

asked Nov 25, 2017 at 11:09

4 votes

1 answer

165 views

Computing probability distributions in the two envelope problem

asked Jan 25, 2021 at 20:52

4 votes

1 answer

354 views

What is the probability distribution of summation of two independent random variables conditioned upon one of the summands?

asked Jul 11, 2022 at 4:24

3 votes

1 answer

167 views

What does it mean for a sequence of random vectors to converge to a random vector?

asked Jul 28, 2022 at 5:04

3 votes

1 answer

54 views

Is the assumption of a diagonal covariance matrix on the latent space in a variational autoencoder in any way restrictive?

asked Feb 19 at 7:32

3 votes

1 answer

96 views

Geometric understanding of linear regression

asked Feb 22 at 16:16

3 votes

2 answers

161 views

A question about linear regression results

asked Feb 23 at 17:07

3 votes

1 answer

64 views

In Expectation-Maximization, in the maximization step, do we maximize expectation of the log likelihood (wikipedia) or evidence lower bound (cs 229)?

asked Jul 8 at 11:36

3 votes

1 answer

122 views

Deriving PCA solution using infinitesimals

asked Sep 6, 2017 at 13:47

3 votes

1 answer

676 views

Batch normalization variance calculation

asked Oct 31, 2017 at 20:00

3 votes

2 answers

3k views

starting off with same weights in neural networks

asked Apr 3, 2017 at 4:57

3 votes

2 answers

4k views

Why word2vec maximizes the cosine similarity between semantically similar words

asked Jan 25, 2018 at 1:12

3 votes

1 answer

211 views

How do we pass data to a RNN?

asked Feb 18, 2018 at 0:25

3 votes

2 answers

2k views

What are the final predictions in tree based models?

asked Jun 27, 2018 at 12:58

3 votes

1 answer

329 views

A confusion about Bayes's theorem

asked Nov 2, 2018 at 14:50

2 votes

0 answers

260 views

Why is dropout a good fit for ReLU units?

asked Jul 26, 2018 at 14:02

2 votes

1 answer

2k views

how to choose model when training accuracy is lower than validation accuracy while training neural network?

asked Oct 16, 2018 at 13:20

Stack Exchange Network

68 Questions

What are the implications of scaling the features to xgboost?

Neural networks vs everything else

Why go through the trouble of expectation maximization and not use gradient descent?

Why maximizing the lower bound of variational evidence maximizes the probability of observing data

Is a policy always deterministic in reinforcement learning?

Understanding batch normalization

Explaining dimensionality reduction using SVD (without reference to PCA)

What is the output of a tf.nn.dynamic_rnn()?

Why is rejection of null hypothesis not a case of prosecutor's fallacy?

Understanding semi supervised technique called mean teachers

Does a Binomial converge to Poisson or Normal?

why can two random variables be added only when they have the same domain?

Understanding regularization in xgboost

If z is uniform normal is $f(z;\theta)$ a normal distribution

Computing probability distributions in the two envelope problem

What is the probability distribution of summation of two independent random variables conditioned upon one of the summands?

What does it mean for a sequence of random vectors to converge to a random vector?

Is the assumption of a diagonal covariance matrix on the latent space in a variational autoencoder in any way restrictive?

Geometric understanding of linear regression

A question about linear regression results

In Expectation-Maximization, in the maximization step, do we maximize expectation of the log likelihood (wikipedia) or evidence lower bound (cs 229)?

Deriving PCA solution using infinitesimals

Batch normalization variance calculation

starting off with same weights in neural networks

Why word2vec maximizes the cosine similarity between semantically similar words

How do we pass data to a RNN?

What are the final predictions in tree based models?

A confusion about Bayes's theorem

Why is dropout a good fit for ReLU units?

how to choose model when training accuracy is lower than validation accuracy while training neural network?