Valentin Calomme's user avatar
Valentin Calomme's user avatar
Valentin Calomme's user avatar
Valentin Calomme
  • Member for 6 years, 6 months
  • Last seen this week
47 votes

Why should the data be shuffled for machine learning tasks

40 votes

In supervised learning, why is it bad to have correlated features?

20 votes
Accepted

Is over fitting okay if test accuracy is high enough?

17 votes

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

11 votes
Accepted

Address parsing using spaCy

8 votes

Different number of features in train vs test

8 votes
Accepted

Does image's background matter for detector training (CNN)?

6 votes

Naive about which Naive Bayes in article

6 votes
Accepted

How distribution of data effects model performance?

6 votes
Accepted

Effect of Stop-Word Removal on Transformers for Text Classification

5 votes

Why are character level models considered less effective than word level models?

5 votes

Why do we need to handle data imbalance?

5 votes
Accepted

Why are RNN/LSTM preferred in time series analysis and not other NN?

5 votes

Using TF-IDF with other features in scikit-learn

5 votes
Accepted

Detect if word is «common English» word or slang word

4 votes

Linear Regression + KFold cross validation

4 votes

Overfitting Naive Bayes

4 votes

What are the disadvantages of Azure's ML vs a pure code approach (R/SKlearn)

4 votes
Accepted

Can BRAT be used for text classification annotation?

4 votes

N-grams in NLP deep learning

4 votes
Accepted

How to set different weights for different training samples?

4 votes
Accepted

Is a BiLSTM layer required if we use BERT?

4 votes
Accepted

Transformer decoder output - how is it linear?

4 votes
Accepted

Nice real data sets for testing DBSCAN?

4 votes
Accepted

Which target variable should I use?

4 votes
Accepted

Are weights of a neural network reset between epochs?

4 votes
Accepted

Why is dictionary-based approach a heuristic method?

4 votes
Accepted

will ANN identify a feature that has no influence?

3 votes
Accepted

How exactly do decision trees split the input region?

3 votes

Cross-attention mask in Transformers

1
2 3 4 5
7