User anymous.asker

5 votes

Accepted

Is it better to have binary features rather than class ones

answered Jul 3, 2017 at 15:52

5 votes

Accepted

Generating Polynomial Features in R

answered Dec 19, 2018 at 17:31

3 votes

Why is deep learning used in recommender systems?

answered Jan 1, 2021 at 12:40

3 votes

Accepted

Should I standardize first or generate polynomials first?

answered Jul 19, 2017 at 18:01

2 votes

Model with rank as the dependent variable?

answered Sep 14, 2017 at 16:24

2 votes

Learning to rank: construct absolute ranking using pair-wise ranking approach

answered Sep 14, 2017 at 16:32

2 votes

How to overcome the class imbalance issue in a text classification problem?

answered Jul 3, 2017 at 15:24

2 votes

Multivariate outlier detection with isolation forest..How to detect most effective features?

answered Oct 4, 2018 at 21:59

2 votes

Accepted

Minimizing an upper bound of objective function

answered Oct 4, 2018 at 22:23

2 votes

Accepted

Linear optimization problem of $argmin$

answered Jan 16, 2019 at 19:31

1 vote

Restricting a weight vector (optimization parameter) to be in a certain domain using python ML library linear regression model

answered Jan 1, 2019 at 10:23

1 vote

Is gradient descent slower for finite differences?

answered Oct 14, 2018 at 10:24

1 vote

Accepted

packages installed after activating conda environment

answered Oct 14, 2018 at 10:57

1 vote

Similarity of Dictionaries Using Cosine Similarity

answered Oct 17, 2018 at 20:52

1 vote

What advantage does Gaussian kernel have than any other kernels, such as linear kernel, polynomial kernel and so on?

answered Oct 31, 2018 at 17:25

1 vote

Minimization algorithm that can consider gradient close to solution

answered Nov 9, 2018 at 8:40

1 vote

Accepted

Objective function for multi-label classification

answered Nov 10, 2018 at 16:40

1 vote

Collaborative filtering with human-adjusted latent factors

answered Oct 9, 2018 at 16:35

1 vote

Can preprocessing the whole population cause data leakage?

answered Oct 9, 2018 at 16:44

1 vote

Logistic Regression Cost Function: Gives mathematical error since its attempting to calculate log(0)

answered Oct 11, 2018 at 21:01

1 vote

Accepted

Do unique values has to be removed ?

answered Jul 3, 2017 at 15:42

1 vote

Binary classification of partially labeled data

answered Jul 3, 2017 at 15:59

1 vote

Learning comparisons

answered Sep 14, 2017 at 16:35

1 vote

What does "intractable" mean for this function in latent Dirichlet allocation (LDA)?

answered Jul 13, 2021 at 0:27

1 vote

How to prevent a neural network from outputing too clustered probabilities?

answered Jan 6, 2019 at 14:36

0 votes

Why does Light GBM model produce different results while testing?

answered Jul 13, 2021 at 0:31

0 votes

Accepted

Maximum likelihood estimation vs calculating distribution parameters "manually"

answered Oct 4, 2018 at 21:32

0 votes

K-means with categorical data

answered Jul 15, 2017 at 10:16

0 votes

Class weights for imbalanced data in multilabel problems

answered Oct 12, 2018 at 10:01

0 votes

Accepted

Free parameters in logistic regression

answered Oct 13, 2018 at 21:52

Stack Exchange Network

42 Answers

Is it better to have binary features rather than class ones

Generating Polynomial Features in R

Why is deep learning used in recommender systems?

Should I standardize first or generate polynomials first?

Model with rank as the dependent variable?

Learning to rank: construct absolute ranking using pair-wise ranking approach

How to overcome the class imbalance issue in a text classification problem?

Multivariate outlier detection with isolation forest..How to detect most effective features?

Minimizing an upper bound of objective function

Linear optimization problem of $argmin$

Restricting a weight vector (optimization parameter) to be in a certain domain using python ML library linear regression model

Is gradient descent slower for finite differences?

packages installed after activating conda environment

Similarity of Dictionaries Using Cosine Similarity

What advantage does Gaussian kernel have than any other kernels, such as linear kernel, polynomial kernel and so on?

Minimization algorithm that can consider gradient close to solution

Objective function for multi-label classification

Collaborative filtering with human-adjusted latent factors

Can preprocessing the whole population cause data leakage?

Logistic Regression Cost Function: Gives mathematical error since its attempting to calculate log(0)

Do unique values has to be removed ?

Binary classification of partially labeled data

Learning comparisons

What does "intractable" mean for this function in latent Dirichlet allocation (LDA)?

How to prevent a neural network from outputing too clustered probabilities?

Why does Light GBM model produce different results while testing?

Maximum likelihood estimation vs calculating distribution parameters "manually"

K-means with categorical data

Class weights for imbalanced data in multilabel problems

Free parameters in logistic regression