Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. 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 3 Bountied Hot Week Month

0

votes

0

answers

2

views

How to explain that a same DNN model have radically different behaviours with each new initialization and training?

regression relu weights-initialization fully-connected-layer learning-curve

asked 28 mins ago Daviiid 193

0

votes

1

answer

19

views

Predict time series from initial non-time dependant parameters

recurrent-neural-networks ai-basics time-series

answered 1 hour ago Mike NZ 101

2

votes

2

answers

44

views

Maximize loss on non-target variable

neural-networks loss-functions

modified 4 hours ago Community♦ 1

0

votes

0

answers

9

views

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

neural-networks deep-learning convolutional-neural-networks long-short-term-memory text-classification

asked 4 hours ago moooo112 1

0

votes

0

answers

15

views

Can I use binary numbers and plain floats in the same neural network input for reinforcement learning?

reinforcement-learning tensorflow python

modified 7 hours ago Lucas Pelizzari 21

1

vote

1

answer

9

views

Expected behavior of adversarial attacks on deep NN?

machine-learning deep-learning convolutional-neural-networks adversarial-ml

answered 8 hours ago htl 487

1

vote

0

answers

10

views

What are the consequences of layer norm vs batch norm?

deep-learning batch-normalization

modified 8 hours ago htl 487

2

votes

0

answers

43

views

+50

What's the difference between content-based attention and dot-product attention?

neural-networks attention seq2seq

modified 8 hours ago Alexander Soare 992

1

vote

1

answer

14

views

How to train an LSTM to classify based on rare historic event?

deep-learning reference-request recurrent-neural-networks long-short-term-memory time-series

answered 9 hours ago Kostya 499

1

vote

1

answer

33

views

Number of parameters in Keras/Tensorflow Dense layers

neural-networks tensorflow keras

modified 9 hours ago Kashan 315

0

votes

0

answers

13

views

Can a siamese neural network distinguish expected from unexpected changes?

deep-learning similarity siamese-neural-network

asked 9 hours ago user46246 1

0

votes

1

answer

57

views

What are some good papers or resources for aspect extraction and opinion modelling from video or audio?

deep-learning computer-vision feature-extraction sentiment-analysis data-mining

modified 10 hours ago Community♦ 1

6

votes

2

answers

232

views

Why is dropout favoured compared to reducing the number of units in hidden layers?

neural-networks machine-learning deep-learning dropout regularization

modified 10 hours ago Faizy 539

6

votes

2

answers

5k

views

How to use CNN for making predictions on non-image data?

convolutional-neural-networks tensorflow

modified 10 hours ago Faizy 539

Browse more Questions

Artificial Intelligence Stack Exchange works best with JavaScript enabled