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 2 Bountied Hot Week Month

2

votes

2

answers

17

views

Why does the bias need to be a vector in a neural network?

neural-networks deep-learning tensorflow javascript

modified 1 hour ago nbro 10.9k

1

vote

0

answers

8

views

How to build sort objects model using Deep Learning

neural-networks tensorflow python

asked 10 hours ago NobDev 11

1

vote

0

answers

28

views

How is clustering used in the unsupervised training of a neural network?

neural-networks machine-learning unsupervised-learning clustering

modified yesterday nbro 10.9k

3

votes

1

answer

63

views

Can we get the inverse of the function that a neural network represents?

neural-networks deep-learning python math

modified yesterday respectful 925

2

votes

0

answers

10

views

Can Bert be used to extract embedding for large categorical features?

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

asked yesterday user_12 121

2

votes

1

answer

62

views

Is it possible to train a neural network with 3 inputs and 12 outputs?

neural-networks matlab neural-architecture-search thought-vectors

modified yesterday nbro 10.9k

1

vote

1

answer

42

views

How is back-propagation useful in neural networks?

neural-networks deep-learning backpropagation

answered 2 days ago Matias Valdenegro 146

3

votes

0

answers

72

views

+50

Why do regression LSTMs learn high to low inputs significantly better than low to high?

neural-networks long-short-term-memory

modified 2 days ago Recessive 668

0

votes

2

answers

138

views

Why am I getting spikes in the values of the loss function during training?

neural-networks machine-learning keras loss-functions

modified 2 days ago Community♦ 1

2

votes

1

answer

22

views

Is greedy layer-wise pretraining obsolete?

neural-networks

answered Jan 17 at 15:57 mshlis 1,675

1

vote

0

answers

8

views

Regional specialization in neural networks (especially for language processing)?

neural-networks reference-request artificial-neuron neural-architecture-search

modified Jan 17 at 8:36 TomR 675

6

votes

3

answers

137

views

Why do neural networks trained on identical datasets and with identical hyper-parameters have different performances?

neural-networks machine-learning training

modified Jan 17 at 7:01 Community♦ 1

2

votes

0

answers

31

views

How can I compare EEG data with accelerometer data in 1 algorithm?

neural-networks deep-learning comparison datasets computational-linguistics

modified Jan 16 at 22:58 nbro 10.9k

1

vote

0

answers

22

views

What activation functions are better for what problems?

neural-networks deep-learning activation-function

modified Jan 16 at 11:20 nbro 10.9k

Browse more Questions

Artificial Intelligence Stack Exchange works best with JavaScript enabled