Most popular questions

242 What are deconvolutional layers? 2015-06-13T09:56:45.397

212 How to set class weights for imbalanced classes in Keras? 2016-08-17T09:35:45.110

200 What's the difference between fit and fit_transform in scikit-learn models? 2016-06-21T10:05:08.587

200 Micro Average vs Macro average Performance in a Multiclass classification setting 2016-12-29T17:39:07.967

190 Publicly Available Datasets 2014-05-18T18:45:38.957

173 K-Means clustering for mixed numeric and categorical data 2014-05-14T05:58:21.927

154 What is the "dying ReLU" problem in neural networks? 2015-05-07T04:11:56.600

146 Best python library for neural networks 2014-07-07T19:17:04.973

146 Difference between isna() and isnull() in pandas 2018-09-06T10:14:01.593

145 When to use One Hot Encoding vs LabelEncoder vs DictVectorizor? 2015-12-19T19:30:35.527

143 When to use GRU over LSTM? 2016-10-17T11:47:45.340

140 How to draw Deep learning network architecture diagrams? 2016-11-03T03:10:24.893

138 The cross-entropy error function in neural networks 2015-12-10T06:22:48.927

126 How do you visualize neural network architectures? 2016-07-18T17:08:17.237

119 Python vs R for machine learning 2014-06-12T06:04:48.243

114 Why do people prefer Pandas to SQL? 2018-07-12T09:25:51.067

111 Train/Test/Validation Set Splitting in Sklearn 2016-11-15T14:55:04.130

101 Choosing a learning rate 2014-06-16T18:08:38.623

101 SVM using scikit learn runs endlessly and never completes execution 2014-08-18T10:46:57.360

100 Training an RNN with examples of different lengths in Keras 2018-01-06T23:41:20.297

98 How to get correlation between two categorical variable and a categorical variable and continuous variable? 2014-08-03T13:07:24.143

98 Why do cost functions use the square error? 2016-02-10T21:52:30.730

91 How big is big data? 2014-05-14T03:56:20.963

89 When should I use Gini Impurity as opposed to Information Gain (Entropy)? 2016-02-12T22:05:41.193

89 Backprop Through Max-Pooling Layers? 2016-05-12T08:38:12.740

86 Advantages of AUC vs standard accuracy 2014-07-22T03:43:20.327

80 Time series prediction using ARIMA vs LSTM 2016-07-11T16:45:21.020

78 ValueError: Input contains NaN, infinity or a value too large for dtype('float32') 2016-05-26T04:13:04.033

77 How are 1x1 convolutions the same as a fully connected layer? 2016-07-17T13:23:22.600

77 Data scientist vs machine learning engineer 2018-02-20T06:15:04.687

76 strings as features in decision tree/random forest 2015-02-25T01:07:14.717

75 When to use (He or Glorot) normal initialization over uniform init? And what are its effects with Batch Normalization? 2016-07-28T17:12:29.933

69 Are Support Vector Machines still considered "state of the art" in their niche? 2014-07-09T12:22:22.400

69 Open source Anomaly Detection in Python 2015-07-22T14:26:58.660

67 What is dimensionality reduction? What is the difference between feature selection and extraction? 2014-05-18T06:26:15.673

64 When is a Model Underfitted? 2014-06-13T16:44:29.323

62 Clustering geo location coordinates (lat,long pairs) 2014-07-17T09:50:41.437

62 In supervised learning, why is it bad to have correlated features? 2017-11-07T14:37:41.993

62 Convert a list of lists into a Pandas Dataframe 2018-01-05T18:40:33.767

61 Tools and protocol for reproducible data science using Python 2014-07-16T20:09:08.640

61 Adding Features To Time Series Model LSTM 2017-02-21T22:17:40.000

59 Cosine similarity versus dot product as distance metrics 2014-07-15T21:30:11.600

59 RNN vs CNN at a high level 2016-05-06T14:36:20.190

58 Latent Dirichlet Allocation vs Hierarchical Dirichlet Process 2014-05-18T06:10:52.543

58 Neural networks: which cost function to use? 2016-01-19T11:48:29.337

58 What is the difference between "equivariant to translation" and "invariant to translation" 2017-01-04T08:41:15.700

57 Machine learning - features engineering from date/time data 2014-10-29T05:25:55.603

57 Why do internet companies prefer Java/Python for data scientist job? 2016-08-18T05:05:45.470

56 Why mini batch size is better than one single "batch" with all training data? 2017-02-07T12:40:25.200

55 How to fight underfitting in a deep neural net 2014-07-13T09:04:39.703