user avatar
user avatar
user avatar
Ben Reiniger
Moderator
  • Member for 4 years, 1 month
  • Last seen this week
155 votes
19 answers
185k views

How do you visualize neural network architectures?

  • 17.6k
59 votes
5 answers
24k views

In softmax classifier, why use exp function to do normalization?

  • 693
55 votes
6 answers
15k views

Should I go for a 'balanced' dataset or a 'representative' dataset?

  • 653
45 votes
5 answers
22k views

Is it always better to use the whole dataset to train the final model?

  • 3,740
19 votes
4 answers
43k views

L2 loss vs. mean squared loss

  • 2,505
15 votes
3 answers
16k views

L1 & L2 Regularization in Light GBM

12 votes
2 answers
4k views

What is the proper way to use early stopping with cross-validation?

11 votes
2 answers
2k views

What is the most efficient method for hyperparameter optimization in scikit-learn?

8 votes
2 answers
104 views

Model for Differing Number of Rows per Observation

  • 181
8 votes
2 answers
199 views

Time-series prediction: Model & data assumptions in AI/ML models vs conventional models

  • 538
8 votes
2 answers
89 views

Which classification algorithms are negatively affected by class imbalances?

8 votes
2 answers
2k views

Transformer model: Why are word embeddings scaled before adding positional encodings?

7 votes
2 answers
305 views

Dropping features after final evaluation on test data

7 votes
1 answer
553 views

Reticulate vs Python

  • 2,915
7 votes
4 answers
2k views

Can the vanishing gradient problem be solved by multiplying the input of tanh with a coefficient?

  • 121
6 votes
1 answer
480 views

Strategies for handling unlabeled data which is slightly different from the labeled data

  • 69
6 votes
1 answer
863 views

Understanding LSTM structure

  • 161
6 votes
1 answer
2k views

Smart data split (train/eval) for Object Detection

6 votes
2 answers
207 views

ground truth fit is worse than cross validated fit on noisy data?

5 votes
3 answers
183 views

How to use "tree boosting" with a data-driven loss function

  • 51
5 votes
1 answer
5k views

svm.LinearSVC: larger max_iter number doesn't always increase the accuracy/precision/recall

  • 281
5 votes
1 answer
1k views

Multiclass classification on imbalanced dataset : Accuracy or micro F1 or macro F1

5 votes
2 answers
117 views

Does a precision score increasing with a higher number of folds mean the model will improve with more data?

5 votes
3 answers
933 views

Quasi-categorical variables - any ideas?

5 votes
1 answer
2k views

My CNN produces volatile validation_loss and does not converge in python(Keras)

5 votes
1 answer
214 views

Feature scaling worsens performance?

  • 151
4 votes
1 answer
1k views

AttributeError: type object 'Lambda' has no attribute 'shape'

  • 584
4 votes
3 answers
444 views

Train classifier on balanced dataset and apply on imbalanced dataset?

4 votes
1 answer
283 views

Hyperopt vs Default Values

  • 571
4 votes
2 answers
3k views

Why does feature scaling improve the convergence speed for gradient descent?

  • 141