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

more tags

Active Hot Week Month

1

vote

1

answer

19

views

What makes GAN or VAE better at image generation than NN that directly maps inputs to images

convolutional-neural-networks generative-adversarial-networks image-generation variational-autoencoder

modified 6 hours ago nbro 10.2k

0

votes

0

answers

6

views

Using U-NET for image semantic segmentation

convolutional-neural-networks loss-functions architecture image-segmentation

asked 8 hours ago VansFannel 387

2

votes

0

answers

52

views

Which neural network should I use to transform the pixels of a video overtime?

machine-learning deep-learning convolutional-neural-networks resource-request

modified 10 hours ago nbro 10.2k

3

votes

1

answer

35

views

Why do current models use multiple normalization layers?

deep-learning convolutional-neural-networks batch-normalization

modified 10 hours ago nbro 10.2k

3

votes

2

answers

73

views

Convolutional Neural Network: does each filter in each convolution layer create a new image?

neural-networks convolutional-neural-networks hidden-layers image-processing convolution

answered yesterday adn 125

1

vote

0

answers

14

views

Is CNN capable of extracting the descriptive statistics features

neural-networks machine-learning convolutional-neural-networks keras

asked yesterday nilsinelabore 195

2

votes

0

answers

30

views

FasterRCNN's RPN network training

neural-networks deep-learning convolutional-neural-networks object-recognition object-detection

modified 2 days ago Michael Heidelberg 121

1

vote

1

answer

82

views

Why should each filter have different weights for each input channel?

machine-learning convolutional-neural-networks parameter

modified Dec 8 at 23:02 Community♦ 1

5

votes

2

answers

630

views

What to do if CNN cannot overfit a training set on adding dropout?

convolutional-neural-networks linear-regression dropout

modified Dec 8 at 19:03 Community♦ 1

2

votes

1

answer

41

views

Can a trained object detection model deal with variations of the input?

machine-learning convolutional-neural-networks object-detection adversarial-ml

modified Dec 8 at 14:34 nbro 10.2k

0

votes

0

answers

34

views

Is there an audio dataset with the corresponding phonemes in the audio?

neural-networks machine-learning convolutional-neural-networks tensorflow datasets

modified Dec 6 at 14:53 nbro 10.2k

1

vote

0

answers

17

views

Optimisation of dependence of efficiency of CNN on training data

deep-learning convolutional-neural-networks regression

asked Dec 6 at 6:15 Solvalou 111

0

votes

1

answer

39

views

structure of neural network for classification problems with large amounts of null classifications

convolutional-neural-networks classification

answered Dec 5 at 20:38 Sammy 254

46

votes

3

answers

29k

views

How can neural networks deal with varying input sizes?

neural-networks machine-learning deep-learning convolutional-neural-networks natural-language-processing

modified Dec 5 at 18:14 voo_doo 103

Browse more Questions

Artificial Intelligence Stack Exchange works best with JavaScript enabled