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 5 Bountied Hot Week Month

0

votes

2

answers

1k

views

Why LSTM models do not require labels for each step?

deep-learning lstm

modified 5 hours ago Community♦ 1

37

votes

5

answers

30k

views

Intuitive explanation of Noise Contrastive Estimation (NCE) loss?

deep-learning tensorflow word-embeddings sampling loss-function

modified 7 hours ago thepurpleowl 3

1

vote

1

answer

14

views

The best practice for implementing a dynamic classification model that can have classes added to it frequently?

machine-learning deep-learning classification

answered 9 hours ago Brian Spiering 12.4k

1

vote

0

answers

8

views

Is it possible for class activation maps where the predicted class has no activations?

deep-learning image-classification pytorch

asked 10 hours ago widepeeposad 11

1

vote

0

answers

9

views

Which layer actually contains attention and how to map with input for classification scenario

deep-learning keras attention-mechanism

modified 12 hours ago Sandeep Bhutani 724

2

votes

1

answer

27

views

MOOC - for causal analysis - no statistics background

machine-learning deep-learning neural-network classification statistics

answered 16 hours ago prashant0598 1,127

1

vote

0

answers

13

views

Text classification - Multiple texts for a single instance (Deep Learning)

deep-learning nlp text-classification

asked 18 hours ago Kuba 11

2

votes

0

answers

15

views

Convolutional autoencoder - why keras example is asymmetry model?

deep-learning keras convolutional-neural-network autoencoder

asked 19 hours ago user3668129 157

0

votes

1

answer

89

views

Dense layer: how to transform hgih dim vector to one dim? (sigmoid function)

machine-learning neural-network deep-learning

modified 21 hours ago Community♦ 1

1

vote

0

answers

19

views

Implementing cosine embedding loss with labels 0 and 1

deep-learning neural-network keras tensorflow loss-function

modified 21 hours ago Audida 11

0

votes

1

answer

168

views

Training the document page layout and classifying good/bad layouts

machine-learning deep-learning nlp cnn rnn

modified yesterday Community♦ 1

0

votes

2

answers

56

views

How to extract contents by topic from a document?

machine-learning deep-learning nlp information-extraction semantic-segmentation

modified yesterday Community♦ 1

0

votes

0

answers

11

views

Can transformers be used to solve for a number of independent polynomial inequalities or polynomial equations?

machine-learning deep-learning transformer mathematics graph-neural-network

asked yesterday sam 1

0

votes

0

answers

8

views

Cartpole - Number of layers and neurons - model hyperparameters

deep-learning reinforcement-learning dqn

asked yesterday vimala 11

Browse more Questions

Data Science Stack Exchange works best with JavaScript enabled