user avatar
user avatar
user avatar
Dani Mesejo
  • Member for 5 years, 9 months
  • Last seen more than a month ago
24 votes
Accepted

How to calculate mAP for detection task for the PASCAL VOC Challenge?

9 votes

Best practical algorithm for sentence similarity

8 votes
Accepted

Price prediction based on historic data

8 votes
Accepted

Feature agglomeration: Is it testing interactions?

7 votes
Accepted

Weighted sum of word vectors for document similarity

6 votes
Accepted

Predicting Missing Features

6 votes
Accepted

Could not convert string to float error on KDDCup99 dataset

6 votes

Normalized output of machine learning

5 votes

Pattern Recognition on Financial Market

5 votes
Accepted

Why should softmax be used in CNN

5 votes

Calculate similarity on boolean data

4 votes

Training data set for food image recognition

4 votes

Is there an overview over recommender system architectures?

4 votes

can accuracy rise while precision and recall drop?

3 votes

Difference between explicit and implicit density with and without the relation to neural network

3 votes

How to make R or Python as fast as SAS for ODBC Oracle queries?

3 votes
Accepted

Backpropagation in other fields

3 votes
Accepted

Grouping of similar looking text

3 votes

what does smooth/soft probablity mean?

3 votes
Accepted

Are there libraries or techniques for 'noisifying' text data?

2 votes
Accepted

What exactly is a class in kNN search?

2 votes

Columns with no (or nearly no) differences between rows worth keeping?

2 votes
Accepted

How to find a similarity value between cars

2 votes

Softmax classifier never allows for 100% probability in LSTM?

2 votes

Why do we do citation analysis?

2 votes
Accepted

Check similarity of table/csv of Product Names

2 votes
Accepted

How to create a training set for sequence labelling

2 votes
Accepted

What approaches could be used to teach a model to make appropriate brush strokes to reproduce a painting?

2 votes

Populate column based on previous row with a twist

2 votes

Metric to combine average with number of accurance