Marzi Heidari's user avatar
Marzi Heidari's user avatar
Marzi Heidari's user avatar
Marzi Heidari
  • Member for 5 years, 7 months
  • Last seen more than a month ago
3 votes
1 answer
404 views

Why categorical cross entropy loss is not correlated with NLP scores?

2 votes
1 answer
5k views

Why is my model accuracy decreasing after the second epoch?

2 votes
1 answer
4k views

what is label shift?

1 vote
1 answer
331 views

Is it right to maintain the train distribution in test set for unbalanced data?

1 vote
0 answers
69 views

split text data to train and test according to its word distribution

1 vote
1 answer
248 views

distribution difference between image and text

1 vote
1 answer
60 views

Are LDA clusters identical across different runs?

1 vote
1 answer
142 views

Should number of classes be the same in few shot learning train and test?

1 vote
1 answer
84 views

Can't understand an MSE loss function in a paper

0 votes
0 answers
33 views

Acquiring Ground Truth for ISIC 2019 Challenge Test Set for Publication Purposes

0 votes
3 answers
140 views

How to know when to stop trainning a deep network?

0 votes
0 answers
191 views

LSTM Train accuracy decreases in training time during the epoch

0 votes
1 answer
120 views

Difference between prototype and centroid