Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.

Sign up to join this community

Anybody can ask a question

Anybody can answer

The best answers are voted up and rise to the top

Explore our Questions

Ask Question

more tags

Active 2 Bountied Hot Week Month

0

votes

1

answer

4

views

Do weights of keywords for each topic add up to 1 in topic modeling?

topic-model

answered 8 mins ago Jayaram Iyer 131

2

votes

1

answer

111

views

Follow Up Question - Why use fit when already have fit_transform?

python scikit-learn

modified 43 mins ago oW_♦ 5,554

0

votes

0

answers

5

views

Help with Classification using scikit-learn models

scikit-learn multiclass-classification hyperparameter

asked 1 hour ago idkfa.bfg2 11

0

votes

1

answer

38

views

Absolute-value max pooling in 2D convolutional neural networks

machine-learning cnn pooling

modified 1 hour ago Community♦ 1

0

votes

1

answer

21

views

Issue replicating AutoKeras StructuredDataClassifier

keras tensorflow

answered 1 hour ago AlwaysNull 61

0

votes

0

answers

3

views

Why are convolutions still used in some Transformer networks for speech enhancement?

machine-learning transformer attention-mechanism

asked 2 hours ago J. Herrera 23

1

vote

2

answers

15

views

How to measure the contribution of each input channel to a network's accuracy?

deep-learning

answered 2 hours ago Jaliborc 11

0

votes

0

answers

2

views

How does Wav2Vec 2.0 feed output from Convolutional Feature Encoder as input to the Transformer Context Network

speech-to-text

asked 2 hours ago user116029 1

0

votes

1

answer

31

views

Does autoencoder with few images not work?

machine-learning python autoencoder

modified 4 hours ago Community♦ 1

0

votes

1

answer

27

views

Solution for TF-IDF Vectorization in Angular project?

machine-learning scikit-learn tfidf javascript

modified 4 hours ago Community♦ 1

0

votes

1

answer

13

views

Advantages of CNN vs. LSTM for sequence data like text or log-files

deep-learning cnn lstm text sequence

answered 5 hours ago neuroguy123 101

0

votes

0

answers

5

views

How to JUST represent words as embeddings by pretrained BERT?

nlp unsupervised-learning word-embeddings bert representation

asked 5 hours ago taciturno 23

1

vote

0

answers

14

views

Building a multiclass classifier that can handle classes it has never seen?

machine-learning classification word-embeddings

modified 6 hours ago Johngianni 11

0

votes

0

answers

10

views

Should we also include negative instance in cross-validation process of one-class classifiers?

nlp natural-language-process classifier

asked 6 hours ago LGDGODV 35

Browse more Questions

Data Science Stack Exchange works best with JavaScript enabled