user avatar
user avatar
user avatar
volperossa
  • Member for 8 years, 1 month
  • Last seen more than a week ago
530 votes
23 answers
286k views

Why square the difference instead of taking the absolute value in standard deviation?

  • 5,545
372 votes
7 answers
1.5m views

How to normalize data to 0-1 range?

  • 4,101
347 votes
5 answers
371k views

What is the trade-off between batch size and number of iterations to train a neural network?

239 votes
4 answers
108k views

ROC vs precision-and-recall curves

144 votes
8 answers
88k views

Why L1 norm for sparse models

  • 1,623
94 votes
8 answers
126k views

How to compute precision/recall for multiclass-multilabel classification?

  • 1,265
87 votes
6 answers
58k views

Why is the L2 regularization equivalent to Gaussian prior?

  • 1,179
81 votes
2 answers
145k views

How to normalize data between -1 and 1?

  • 1,129
78 votes
6 answers
109k views

What are good initial weights in a neural network?

  • 907
77 votes
3 answers
69k views

What is the difference between ZCA whitening and PCA whitening?

  • 11.7k
74 votes
1 answer
60k views

What are the shortcomings of the Mean Absolute Percentage Error (MAPE)?

64 votes
3 answers
61k views

Clustering with K-Means and EM: how are they related?

  • 793
61 votes
5 answers
139k views

Backpropagation with Softmax / Cross Entropy

  • 713
60 votes
4 answers
77k views

What is the definition of a "feature map" (aka "activation map") in a convolutional neural network?

  • 703
59 votes
5 answers
125k views

Which loss function is correct for logistic regression?

  • 724
48 votes
6 answers
49k views

Why zero correlation does not necessarily imply independence

  • 6,055
46 votes
4 answers
19k views

What are the factors that cause the posterior distributions to be intractable?

  • 3,377
43 votes
5 answers
49k views

Entropy of an image

42 votes
4 answers
14k views

How can SVM 'find' an infinite feature space where linear separation is always possible?

  • 561
33 votes
6 answers
28k views

What is difference between 'transfer learning' and 'domain adaptation'?

  • 1,817
31 votes
1 answer
7k views

Who invented k-fold cross-validation?

27 votes
1 answer
7k views

Backpropagation on a convolutional layer

  • 531
22 votes
3 answers
7k views

Backpropagation algorithm and error in hidden layer

  • 489
22 votes
3 answers
28k views

Why do we divide by the standard deviation and not some other standardizing factor before doing PCA?

21 votes
4 answers
51k views

Comparing two histograms using Chi-Square distance

19 votes
3 answers
13k views

How to do data augmentation and train-validate split?

  • 293
17 votes
4 answers
35k views

In CNN, are upsampling and transpose convolution the same?

  • 11.7k
15 votes
1 answer
8k views

Softmax overflow [closed]

  • 163
14 votes
3 answers
24k views

What is the difference between linearly dependent and linearly correlated?

13 votes
5 answers
5k views

Intuition on the definition of the covariance