User Aditya

271 votes

12 answers

257k views

What are deconvolutional layers?

Martin Thoma

17.6k

asked Jun 13, 2015 at 9:56

263 votes

8 answers

314k views

Micro Average vs Macro average Performance in a Multiclass classification setting

multiclass-classification evaluation

SHASHANK GUPTA

3,535

asked Dec 29, 2016 at 17:39

248 votes

10 answers

361k views

How to set class weights for imbalanced classes in Keras?

deep-learning classification keras weighted-data

Hendrik

7,947

asked Aug 17, 2016 at 9:35

180 votes

5 answers

127k views

What is the "dying ReLU" problem in neural networks?

machine-learning neural-network deep-learning

tejaskhot

3,815

asked May 7, 2015 at 4:11

170 votes

6 answers

163k views

When to use GRU over LSTM?

neural-network deep-learning lstm gru

Sayali Sonawane

1,931

asked Oct 17, 2016 at 11:47

147 votes

6 answers

163k views

The cross-entropy error function in neural networks

machine-learning tensorflow

Martin Thoma

17.6k

asked Dec 10, 2015 at 6:22

124 votes

1 answer

355k views

How to get correlation between two categorical variable and a categorical variable and continuous variable?

r statistics correlation

GeorgeOfTheRF

1,908

asked Aug 3, 2014 at 13:07

112 votes

12 answers

131k views

SVM using scikit learn runs endlessly and never completes execution

python svm scikit-learn

tejaskhot

3,815

asked Aug 18, 2014 at 10:46

106 votes

5 answers

65k views

Why do cost functions use the square error?

machine-learning linear-regression loss-function

Golo Roden

1,233

asked Feb 10, 2016 at 21:52

92 votes

12 answers

19k views

How big is big data?

bigdata scalability efficiency performance

Rubens

4,027

asked May 14, 2014 at 3:56

85 votes

7 answers

60k views

Time series prediction using ARIMA vs LSTM

time-series deep-learning rnn prediction

ahajib

1,065

asked Jul 11, 2016 at 16:45

82 votes

6 answers

132k views

strings as features in decision tree/random forest

machine-learning python scikit-learn random-forest decision-trees

user3001408

955

asked Feb 25, 2015 at 1:07

78 votes

4 answers

63k views

What is the positional encoding in the transformer model?

nlp encoding attention-mechanism transformer

Peyman

883

asked Apr 28, 2019 at 14:43

71 votes

5 answers

106k views

GBM vs XGBOOST? Key differences?

machine-learning algorithms xgboost ensemble-modeling gbm

Aman

877

asked Feb 11, 2017 at 20:03

69 votes

11 answers

38k views

What is dimensionality reduction? What is the difference between feature selection and extraction?

feature-selection feature-extraction dimensionality-reduction

alvas

2,392

asked May 18, 2014 at 6:26

69 votes

6 answers

138k views

Cross-entropy loss explanation

machine-learning neural-network deep-learning softmax

enterML

2,921

asked Jul 10, 2017 at 10:26

66 votes

5 answers

44k views

Adding Features To Time Series Model LSTM

machine-learning neural-network deep-learning time-series

Rjay155

1,145

asked Feb 21, 2017 at 22:17

63 votes

9 answers

95k views

Clustering geo location coordinates (lat,long pairs)

machine-learning python clustering k-means geospatial

rok

773

asked Jul 17, 2014 at 9:50

58 votes

5 answers

52k views

Neural networks: which cost function to use?

machine-learning python neural-network statistics tensorflow

daniel451

703

asked Jan 19, 2016 at 11:48

50 votes

5 answers

29k views

How do subsequent convolution layers work?

neural-network convolutional-neural-network

Martin Thoma

17.6k

asked Dec 2, 2015 at 21:53

42 votes

5 answers

36k views

Intuitive explanation of Noise Contrastive Estimation (NCE) loss?

deep-learning tensorflow word-embeddings sampling loss-function

tejaskhot

3,815

asked Aug 5, 2016 at 3:36

40 votes

9 answers

23k views

Why are Machine Learning models called black boxes?

machine-learning terminology

Dawny33

8,036

asked Aug 17, 2017 at 11:53

40 votes

2 answers

22k views

LightGBM vs XGBoost

xgboost

Sergey Nizhevyasov

513

asked May 11, 2017 at 12:12

39 votes

6 answers

49k views

Are there free cloud services to train machine learning models?

machine-learning neural-network deep-learning cloud-computing

Green Falcon

13.4k

asked Nov 3, 2017 at 12:41

39 votes

1 answer

20k views

The difference between `Dense` and `TimeDistributedDense` of `Keras`

machine-learning neural-network keras

fluency03

493

asked Mar 22, 2016 at 20:04

38 votes

6 answers

9k views

How to set the number of neurons and layers in neural networks

machine-learning neural-network deep-learning hyperparameter hyperparameter-tuning

stk1234

543

asked Jan 13, 2018 at 15:26

37 votes

6 answers

56k views

When would one use Manhattan distance as opposed to Euclidean distance?

machine-learning classification distance

Bitcoin Cash - ADA enthusiast

559

asked Jun 30, 2017 at 6:28

35 votes

1 answer

13k views

Paper: What's the difference between Layer Normalization, Recurrent Batch Normalization (2016), and Batch Normalized RNN (2015)?

deep-learning rnn normalization batch-normalization

Rizky Luthfianto

2,118

asked Jul 23, 2016 at 9:46

33 votes

6 answers

14k views

Why do convolutional neural networks work?

machine-learning deep-learning neural-network cnn convolutional-neural-network

Praise the lord

431

asked Dec 23, 2016 at 12:43

33 votes

3 answers

17k views

What is a good way to transform Cyclic Ordinal attributes?

feature-extraction feature-scaling featurization

Mangat Rai Modi

539

asked Jun 3, 2015 at 5:56

Stack Exchange Network

current community

your communities

more stack exchange communities

134 Bookmarks

What are deconvolutional layers?

Micro Average vs Macro average Performance in a Multiclass classification setting

How to set class weights for imbalanced classes in Keras?

What is the "dying ReLU" problem in neural networks?

When to use GRU over LSTM?

The cross-entropy error function in neural networks

How to get correlation between two categorical variable and a categorical variable and continuous variable?

SVM using scikit learn runs endlessly and never completes execution

Why do cost functions use the square error?

How big is big data?

Time series prediction using ARIMA vs LSTM

strings as features in decision tree/random forest

What is the positional encoding in the transformer model?

GBM vs XGBOOST? Key differences?

What is dimensionality reduction? What is the difference between feature selection and extraction?

Cross-entropy loss explanation

Adding Features To Time Series Model LSTM

Clustering geo location coordinates (lat,long pairs)

Neural networks: which cost function to use?

How do subsequent convolution layers work?

Intuitive explanation of Noise Contrastive Estimation (NCE) loss?

Why are Machine Learning models called black boxes?

LightGBM vs XGBoost

Are there free cloud services to train machine learning models?

The difference between `Dense` and `TimeDistributedDense` of `Keras`

How to set the number of neurons and layers in neural networks

When would one use Manhattan distance as opposed to Euclidean distance?

Paper: What's the difference between Layer Normalization, Recurrent Batch Normalization (2016), and Batch Normalized RNN (2015)?

Why do convolutional neural networks work?

What is a good way to transform Cyclic Ordinal attributes?