Tour
About Us
Meta
Loading…
current community
Stack Exchange
chat
Meta Stack Exchange
your communities
Sign up
or
log in
to customize your list.
more stack exchange communities
company blog
Log in
Stack Exchange
All Sites
Top Users
Digests
Esmailian
top
accounts
reputation
activity
bookmarks
subscriptions
Top Questions
No questions with score of 5 or more
Top Answers
62
What is the positional encoding in the transformer model?
datascience.stackexchange.com
42
How to feed LSTM with different input array sizes?
datascience.stackexchange.com
39
What is GELU activation?
datascience.stackexchange.com
32
What loss function to use for imbalanced classes (using PyTorch)?
datascience.stackexchange.com
25
What is "posterior collapse" phenomenon?
datascience.stackexchange.com
22
Keras vs. tf.keras
datascience.stackexchange.com
21
L2 loss vs. mean squared loss
datascience.stackexchange.com
18
Unbalanced multiclass data with XGBoost
datascience.stackexchange.com
16
Pandas merge column duplicate and sum value
datascience.stackexchange.com
13
How will Occam's Razor principle work in Machine learning
datascience.stackexchange.com
12
Word2Vec how to choose the embedding size parameter
datascience.stackexchange.com
11
How does Naive Bayes classifier work for continuous variables?
datascience.stackexchange.com
11
CNN - imbalanced classes, class weights vs data augmentation
datascience.stackexchange.com
10
When to use Standard Scaler and when Normalizer?
datascience.stackexchange.com
10
Transform an Autoencoder to a Variational Autoencoder?
datascience.stackexchange.com
10
What is fractionally-strided convolution layer?
datascience.stackexchange.com
9
Can the vanishing gradient problem be solved by multiplying the input of tanh with a coefficient?
datascience.stackexchange.com
9
Validation vs. test vs. training accuracy. Which one should I compare for claiming overfit?
datascience.stackexchange.com
8
Source of Arthur Samuel's definition of machine learning
datascience.stackexchange.com
8
Is Gradient Descent central to every optimizer?
datascience.stackexchange.com
7
Why do we need 2 matrices for word2vec or GloVe
datascience.stackexchange.com
7
About sklearn.metrics.average_precision_score documentation
datascience.stackexchange.com
7
How to plot logistic regression decision boundary?
datascience.stackexchange.com
7
Inverse Relationship Between Precision and Recall
datascience.stackexchange.com
6
Terminology: "flat geometry" in the context of clustering
datascience.stackexchange.com
6
How to compare paired count data?
datascience.stackexchange.com
6
Generate predictions that are orthogonal (uncorrelated) to a given variable
datascience.stackexchange.com
6
How do attention mechanisms in RNNs learn weights for a variable length input
datascience.stackexchange.com
6
Kubernetes stuck on ContainerCreating
serverfault.com
6
Padding sequences for neural sequence models (RNNs)
datascience.stackexchange.com
1
2
next
Stack Exchange works best with JavaScript enabled