User seanv507

17 votes

Importance of local response normalization in CNN

answered Apr 11, 2015 at 7:55

16 votes

Random forest is overfitting?

answered Aug 5, 2013 at 14:52

15 votes

Introduction to machine learning for mathematicians

answered Mar 25, 2015 at 20:44

12 votes

Why does logistic regression become unstable when classes are well-separated?

answered Jan 2, 2017 at 8:56

12 votes

Besides the Literary Digest poll of 1936, what are some famous examples of biased samples that led to erroneous conclusions?

answered Oct 14 at 6:47

10 votes

Why are neural networks easily fooled?

answered Oct 25, 2016 at 10:08

10 votes

Accepted

Glivenko-Cantelli Theorem

answered Sep 22, 2014 at 21:24

9 votes

How and why do normalization and feature scaling work?

answered Jul 13, 2013 at 15:00

8 votes

Confounding variables in machine learning predictions?

answered Apr 7, 2017 at 7:36

8 votes

Could we explain the disadvantage of imbalanced data mathematically?

answered Oct 2, 2022 at 9:27

8 votes

Why is it good for inputs to a NN to be uncorrelated?

answered Oct 8, 2022 at 12:58

7 votes

Accepted

What is the meaning of "SGD scales the gradient uniformly in all directions"?

answered May 29 at 9:33

7 votes

Example where the initial random state of a logistic regression matters?

answered Sep 1 at 13:12

7 votes

Why Can't I use Test set as Validation Set

answered Sep 30, 2016 at 17:15

6 votes

I’d like to learn about probability theory, measure theory and finally machine learning. Where do I start?

answered Aug 22, 2016 at 14:37

6 votes

Feature extracted by max pooling vs mean pooling

answered Jul 13, 2017 at 22:17

6 votes

Neural Network for input values optimization

answered Mar 24, 2019 at 14:51

6 votes

How and why does Batch Normalization use moving averages to track the accuracy of the model as it trains?

answered Aug 5, 2019 at 6:12

6 votes

Feature selection with Random Forests

answered Sep 1, 2013 at 21:33

6 votes

What text or tutorials would you recommend for learning machine learning for image processing?

answered Apr 11, 2015 at 19:00

6 votes

What is the difference between data mining, statistics, machine learning and AI?

answered Sep 14, 2014 at 20:04

6 votes

Multinomial logistic regression vs one-vs-rest binary logistic regression

answered Apr 6, 2020 at 19:27

6 votes

Accepted

Does ( P(B|A) - P(B|~A) ) / P(B|A) have a name?

answered Jul 1, 2021 at 21:21

6 votes

Accepted

Is batching a way to avoid local minima?

answered Feb 20, 2022 at 15:37

5 votes

Accepted

Brier score of calibrated probs is worse than non calibrated probs

answered Nov 18, 2020 at 18:51

5 votes

Accepted

Employee churn as time-to-failure/survival analysis?

answered Jan 5, 2020 at 20:18

5 votes

How do you find the KL Divergence between two multi-variable datasets?

answered Mar 22 at 9:54

5 votes

Why don't statisticians use mutual information as a measure of association?

answered Aug 22, 2013 at 9:12

5 votes

Accepted

Why is sqrt(6) used to calculate epsilon for random initialisation of neural networks?

answered Jul 16, 2017 at 13:10

5 votes

What is an intuitive explanation for how PCA turns from a geometric problem (with distances) to a linear algebra problem (with eigenvectors)?

answered Jun 13, 2016 at 21:08

Stack Exchange Network

234 Answers

Importance of local response normalization in CNN

Random forest is overfitting?

Introduction to machine learning for mathematicians

Why does logistic regression become unstable when classes are well-separated?

Besides the Literary Digest poll of 1936, what are some famous examples of biased samples that led to erroneous conclusions?

Why are neural networks easily fooled?

Glivenko-Cantelli Theorem

How and why do normalization and feature scaling work?

Confounding variables in machine learning predictions?

Could we explain the disadvantage of imbalanced data mathematically?

Why is it good for inputs to a NN to be uncorrelated?

What is the meaning of "SGD scales the gradient uniformly in all directions"?

Example where the initial random state of a logistic regression matters?

Why Can't I use Test set as Validation Set

I’d like to learn about probability theory, measure theory and finally machine learning. Where do I start?

Feature extracted by max pooling vs mean pooling

Neural Network for input values optimization

How and why does Batch Normalization use moving averages to track the accuracy of the model as it trains?

Feature selection with Random Forests

What text or tutorials would you recommend for learning machine learning for image processing?

What is the difference between data mining, statistics, machine learning and AI?

Multinomial logistic regression vs one-vs-rest binary logistic regression

Does ( P(B|A) - P(B|~A) ) / P(B|A) have a name?

Is batching a way to avoid local minima?

Brier score of calibrated probs is worse than non calibrated probs

Employee churn as time-to-failure/survival analysis?

How do you find the KL Divergence between two multi-variable datasets?

Why don't statisticians use mutual information as a measure of association?

Why is sqrt(6) used to calculate epsilon for random initialisation of neural networks?

What is an intuitive explanation for how PCA turns from a geometric problem (with distances) to a linear algebra problem (with eigenvectors)?