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 5 Bountied Hot Week Month

3

votes

0

answers

19

views

Is non-negative matrix factorization for machine learning obsolete?

neural-networks machine-learning reference-request applications

modified 16 mins ago nbro♦ 23.8k

0

votes

0

answers

18

views

Is the dimensionality of the query and key tensors in this implementation of the transformer's self-attention correct?

neural-networks tensorflow transformer implementation attention

modified 1 hour ago nbro♦ 23.8k

3

votes

1

answer

73

views

Does a converging (deep) neural network exist for every possible training data?

neural-networks

modified 2 hours ago John Doe 133

4

votes

2

answers

331

views

How to estimate the capacity of a neural network?

neural-networks deep-learning computational-learning-theory vc-dimension capacity

modified 5 hours ago nbro♦ 23.8k

9

votes

3

answers

353

views

Are there any rules of thumb for having some idea of what capacity a neural network needs to have for a given problem?

neural-networks computational-learning-theory regularization vc-dimension capacity

modified 5 hours ago nbro♦ 23.8k

1

vote

1

answer

70

views

If a neural network is a universal function approximator, can it have any prior beliefs?

neural-networks computational-learning-theory universal-approximation-theorems vc-theory no-free-lunch-theorems

modified 5 hours ago DuttaA 5,127

1

vote

0

answers

9

views

For binary classification learning problems, how should I label instances where I'm only 60% sure?

neural-networks classification data-labelling

asked 6 hours ago Alexander Soare 945

15

votes

3

answers

4k

views

Where can I find the proof of the universal approximation theorem?

neural-networks reference-request proofs function-approximation universal-approximation-theorems

modified 6 hours ago AIM_BLB 475

1

vote

0

answers

7

views

Is it possible to ensure the convergence when training a RNN weight on its SVD decomposition?

neural-networks recurrent-neural-networks papers gradient-descent optimization

asked 6 hours ago Nguyễn Duy Minh Khôi 111

53

votes

11

answers

9k

views

What are some well-known problems where neural networks don't do very well?

neural-networks deep-learning reference-request applications

modified 6 hours ago nbro♦ 23.8k

10

votes

2

answers

571

views

What are the learning limitations of neural networks trained with backpropagation?

neural-networks machine-learning backpropagation universal-approximation-theorems computational-learning-theory

modified 6 hours ago nbro♦ 23.8k

0

votes

0

answers

9

views

Is there any neural network model that can perform multiple NLP steps at once?

neural-networks natural-language-processing natural-language-understanding expert-system natural-language-generation

asked 19 hours ago stackypants 1

2

votes

0

answers

27

views

Can neuro-fuzzy systems be used for supervised learning tasks with tabular data?

neural-networks classification applications regression neuro-fuzzy-systems

modified 19 hours ago nbro♦ 23.8k

4

votes

2

answers

72

views

Which linear algebra book should I read to understand vectorized operations?

neural-networks reference-request linear-algebra books calculus

modified 20 hours ago nbro♦ 23.8k

Browse more Questions

Artificial Intelligence Stack Exchange works best with JavaScript enabled