User Revolucion for Monica

4 votes

3 answers

1k views

Using a random forest, would a RandomForest performance be less if I drop the first or the last tree?

asked Oct 5, 2020 at 13:40

2 votes

1 answer

1k views

Why does my cost function return double the expected value?

asked Jan 28, 2018 at 14:44

2 votes

2 answers

7k views

What is the accuracy majority class classifier?

asked Sep 4, 2019 at 17:05

1 vote

0 answers

363 views

Big dataset for multi-class classification can't be dasked and split, normal one can't be handled

asked Sep 12, 2019 at 22:53

1 vote

1 answer

50 views

Remove rows that are too much alike not to be duplicates

asked Sep 14, 2019 at 8:32

1 vote

2 answers

119 views

Improving classifcation when some are less represented?

asked Sep 14, 2019 at 14:32

1 vote

2 answers

291 views

Is fitting two RandomForestClassifiers 500 trees each and average their predicted probabilities on the test set more performant than one with 1000?

asked Oct 5, 2020 at 13:46

1 vote

1 answer

184 views

What can help decrease outliers' influence on non-tree models?

asked Oct 13, 2020 at 14:47

1 vote

1 answer

644 views

How to use the $\chi^2$ test to select the features, that can be String or categorical?

asked Feb 5, 2020 at 9:41

1 vote

0 answers

268 views

How do decision tree works for feature selection?

asked Feb 5, 2020 at 16:49

1 vote

1 answer

81 views

How could a neural network classifer for multilclass problem classify only in one class when a decision tree is more balanced and accurate?

asked Apr 14, 2020 at 16:28

1 vote

0 answers

377 views

How to choose initial theta in simple linear regression?

asked Oct 26, 2020 at 15:34

1 vote

1 answer

67 views

Why does horizontal lines in plt.plot(feature, '.') mean that the data have been properly shuffled?

asked Nov 16, 2020 at 11:12

1 vote

2 answers

69 views

Sentence to word similarity

asked Dec 10, 2020 at 13:58

1 vote

0 answers

48 views

How to interpret integrated gradients in an NLP toxic text classification use-case?

asked Apr 9, 2022 at 14:30

1 vote

0 answers

341 views

How are the embedding and context matrices created and updated in word embedding?

asked May 13, 2022 at 14:48

1 vote

0 answers

11 views

Why calculating how much removed sentences with most contributing words to the result helps to show that a model is "faithful"?

asked May 18, 2022 at 12:41

1 vote

0 answers

12 views

Why, in a classification task, with $n$ input variables, we can obtain all $2^n$ classiﬁcation functions for each possible set of missing inputs?

asked Dec 1, 2022 at 10:05

0 votes

0 answers

12 views

Is the semicolon (;) notation used to indicate operations are performed concurrently in backpropagation algorithm by Bengio?

asked Oct 2, 2023 at 12:12

0 votes

1 answer

666 views

What is hidden in torch.nn that is multiplied by the feature tensor of my data?

asked Aug 8, 2022 at 15:21

0 votes

0 answers

52 views

What methods to get the intention behind questions (time, preferences, ...)?

asked Jun 29, 2020 at 14:12

0 votes

2 answers

217 views

Why does downsampling leads classification to only predict one class?

asked Sep 19, 2019 at 11:29

0 votes

1 answer

99 views

Linear regression doesn't return the expected number of $\beta_i$

asked Oct 15, 2019 at 17:07

0 votes

1 answer

145 views

Grouping similar rows to detect duplicates

asked Sep 11, 2019 at 10:58

0 votes

1 answer

163 views

Pearson correlation make disapear the target column

asked Sep 11, 2019 at 12:16

0 votes

1 answer

437 views

Are Convolutional Neural Networks a one model, multiple output layers.?

asked Mar 12, 2018 at 10:04

-1 votes

1 answer

58 views

Would descriptors of the last hidden layer of two different CNN be the same?

asked Oct 15, 2020 at 13:22

Stack Exchange Network

27 Questions

Using a random forest, would a RandomForest performance be less if I drop the first or the last tree?

Why does my cost function return double the expected value?

What is the accuracy majority class classifier?

Big dataset for multi-class classification can't be dasked and split, normal one can't be handled

Remove rows that are too much alike not to be duplicates

Improving classifcation when some are less represented?

Is fitting two RandomForestClassifiers 500 trees each and average their predicted probabilities on the test set more performant than one with 1000?

What can help decrease outliers' influence on non-tree models?

How to use the $\chi^2$ test to select the features, that can be String or categorical?

How do decision tree works for feature selection?

How could a neural network classifer for multilclass problem classify only in one class when a decision tree is more balanced and accurate?

How to choose initial theta in simple linear regression?

Why does horizontal lines in plt.plot(feature, '.') mean that the data have been properly shuffled?

Sentence to word similarity

How to interpret integrated gradients in an NLP toxic text classification use-case?

How are the embedding and context matrices created and updated in word embedding?

Why calculating how much removed sentences with most contributing words to the result helps to show that a model is "faithful"?

Why, in a classification task, with $n$ input variables, we can obtain all $2^n$ classiﬁcation functions for each possible set of missing inputs?

Is the semicolon (;) notation used to indicate operations are performed concurrently in backpropagation algorithm by Bengio?

What is hidden in torch.nn that is multiplied by the feature tensor of my data?

What methods to get the intention behind questions (time, preferences, ...)?

Why does downsampling leads classification to only predict one class?

Linear regression doesn't return the expected number of $\beta_i$

Grouping similar rows to detect duplicates

Pearson correlation make disapear the target column

Are Convolutional Neural Networks a one model, multiple output layers.?

Would descriptors of the last hidden layer of two different CNN be the same?