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

2

votes

2

answers

40

views

What are the major differences between cost, loss, error, fitness, utility, objective, criterion functions?

deep-learning convolutional-neural-networks terminology loss-functions comparison

answered 6 hours ago Douglas Daseeco 6,223

2

votes

2

answers

38

views

How should we pad an image to be fed in a CNN?

deep-learning convolutional-neural-networks computer-vision image-processing

answered 7 hours ago Douglas Daseeco 6,223

2

votes

2

answers

45

views

Why do we get a three-dimensional output after a convolutional layer?

convolutional-neural-networks computer-vision image-processing convolution

answered 11 hours ago Douglas Daseeco 6,223

3

votes

0

answers

24

views

What is the difference between graph convolution in the spatial vs spectral domain?

convolutional-neural-networks comparison geometric-deep-learning

modified 15 hours ago razvanc92 316

3

votes

3

answers

593

views

Convolutional neural nets and reduction of the layers

deep-learning convolutional-neural-networks

answered 16 hours ago your_boy_gorja 101

2

votes

1

answer

208

views

Dice loss gives binary output whereas binary crossentropy produces probability output map

deep-learning convolutional-neural-networks keras loss-functions

answered 2 days ago n88b 11

3

votes

2

answers

845

views

What is the purpose of “reshaping it into the shape the network expects and scaling it so that all values are in the [0, 1] interval.”?

neural-networks machine-learning deep-learning convolutional-neural-networks

modified 2 days ago Community♦ 1

2

votes

0

answers

18

views

What is the difference between Squeeze-and-excite and bottleneck modules from Mobilenet v2?

neural-networks convolutional-neural-networks comparison papers attention

modified Aug 17 at 15:57 nbro 6,431

1

vote

1

answer

53

views

Dropout causes too much noise for network to train

neural-networks convolutional-neural-networks dropout regularization relu

modified Aug 17 at 11:01 Community♦ 1

0

votes

2

answers

368

views

RTX 2060 vs GTX 1060 6GB for deep learning

deep-learning convolutional-neural-networks matlab hardware-evaluation gpu

answered Aug 16 at 11:53 Huxwell 21

1

vote

0

answers

15

views

Is there any use of using 3D convolutions for traditional images (like cifar10, imagenet)?

deep-learning convolutional-neural-networks

asked Aug 14 at 19:57 Pinocchio 121

0

votes

1

answer

54

views

What is the correct way to read and analyse images in machine learning?

neural-networks deep-learning convolutional-neural-networks

modified Aug 14 at 19:18 brandon 111

1

vote

0

answers

39

views

How to train and update weights of filters

machine-learning deep-learning convolutional-neural-networks backpropagation

asked Aug 14 at 7:29 meow 6

0

votes

0

answers

13

views

How do I recover the 3D structure of a layer after a fully-connected layer?

neural-networks machine-learning deep-learning convolutional-neural-networks

modified Aug 13 at 21:44 nbro 6,431

Browse more Questions

Artificial Intelligence Stack Exchange works best with JavaScript enabled