User Edamame

95 votes

10 answers

444k views

ValueError: Input contains NaN, infinity or a value too large for dtype('float32')

asked May 26, 2016 at 4:13

32 votes

7 answers

78k views

L2 loss vs. mean squared loss

asked Jan 1, 2018 at 1:58

22 votes

7 answers

25k views

Good "frequent sequence mining" packages in Python?

asked Nov 8, 2016 at 12:33

21 votes

4 answers

32k views

Train/Test Split after performing SMOTE

asked Dec 9, 2016 at 0:19

13 votes

3 answers

30k views

Best frequent itemset package in python

asked Feb 5, 2017 at 22:12

10 votes

2 answers

3k views

Relu does have 0 gradient by definition, then why gradient vanish is not a problem for x < 0?

asked May 4, 2016 at 18:17

8 votes

4 answers

6k views

Unbalanced class: class_weight for ML algorithms in Spark MLLib

asked Dec 7, 2016 at 0:08

8 votes

1 answer

4k views

Difference between Gensim word2vec and keras Embedding layer

asked Oct 11, 2019 at 13:25

7 votes

3 answers

2k views

Kerns LSTM kernel

asked Dec 31, 2017 at 23:10

6 votes

2 answers

6k views

What algorithms will stuck in the local minimum?

asked Jun 6, 2018 at 23:11

5 votes

1 answer

2k views

Real world example of Generative model & Discriminative model

asked May 24, 2018 at 5:37

4 votes

1 answer

307 views

How to deal with annotation errors?

asked Oct 21, 2019 at 16:29

4 votes

1 answer

196 views

Best HMM Package

asked Nov 10, 2019 at 17:43

3 votes

1 answer

163 views

reinforcement learning: Decompose a policy gradient

asked Dec 10, 2019 at 23:07

3 votes

1 answer

2k views

Difference between Dueling DQN and Double DQN?

asked May 31, 2019 at 17:46

3 votes

1 answer

122 views

Mixture Density Network: determine the parameters of each Gaussian component

asked Aug 6, 2018 at 21:12

2 votes

2 answers

3k views

Difference between impurity and misclassificaton

asked May 11, 2018 at 17:15

2 votes

1 answer

748 views

LeNet for Convolution network?

asked May 27, 2016 at 22:26

2 votes

2 answers

127 views

Mathematical algorithms to generate labels for training data

asked May 23, 2018 at 5:36

2 votes

1 answer

6k views

will k-means clustering converge to the same results given the same data set?

asked Nov 24, 2019 at 20:39

1 vote

0 answers

824 views

reinforcement learning: PPO vs. DDPG vs. TRPO - difference and intuition

asked Nov 29, 2019 at 17:42

1 vote

1 answer

2k views

Why would batch normalization allows us to use higher learning rate in the neural network?

asked Dec 2, 2019 at 0:12

1 vote

3 answers

531 views

Intuition behind the RNN/LSTM hidden state?

asked Nov 11, 2019 at 20:27

1 vote

0 answers

91 views

chatbot encoder/decoder: why do we need to use chatbot answer as the decoder inputs?

asked Nov 14, 2019 at 6:36

1 vote

2 answers

6k views

how to handle outliers for clustering algorithms?

asked Nov 24, 2019 at 20:27

1 vote

2 answers

152 views

Intuition behind the entropy definition

asked Jul 29, 2019 at 23:36

1 vote

1 answer

835 views

PrefixSpan model input RDD format

asked Sep 26, 2016 at 23:35

1 vote

1 answer

70 views

business ranking based on transaction data

asked May 23, 2018 at 4:49

1 vote

2 answers

2k views

LSTM unit: cell state dimension

asked Dec 31, 2017 at 20:22

1 vote

1 answer

957 views

Why is ElasticNet performs worse than both Lasso and Ridge?

asked Aug 7, 2018 at 22:47

Stack Exchange Network

40 Questions

ValueError: Input contains NaN, infinity or a value too large for dtype('float32')

L2 loss vs. mean squared loss

Good "frequent sequence mining" packages in Python?

Train/Test Split after performing SMOTE

Best frequent itemset package in python

Relu does have 0 gradient by definition, then why gradient vanish is not a problem for x < 0?

Unbalanced class: class_weight for ML algorithms in Spark MLLib

Difference between Gensim word2vec and keras Embedding layer

Kerns LSTM kernel

What algorithms will stuck in the local minimum?

Real world example of Generative model & Discriminative model

How to deal with annotation errors?

Best HMM Package

reinforcement learning: Decompose a policy gradient

Difference between Dueling DQN and Double DQN?

Mixture Density Network: determine the parameters of each Gaussian component

Difference between impurity and misclassificaton

LeNet for Convolution network?

Mathematical algorithms to generate labels for training data

will k-means clustering converge to the same results given the same data set?

reinforcement learning: PPO vs. DDPG vs. TRPO - difference and intuition

Why would batch normalization allows us to use higher learning rate in the neural network?

Intuition behind the RNN/LSTM hidden state?

chatbot encoder/decoder: why do we need to use chatbot answer as the decoder inputs?

how to handle outliers for clustering algorithms?

Intuition behind the entropy definition

PrefixSpan model input RDD format

business ranking based on transaction data

LSTM unit: cell state dimension

Why is ElasticNet performs worse than both Lasso and Ridge?