Hottest Questions This Month

6

votes

1

answer

446

views

What is the formula for the momentum and Adam optimisers?

modified Jan 13 at 22:39 datdinhquoc 451

4

votes

2

answers

430

views

Effect of batch size and number of GPUs on model accuracy

deep-learning tensorflow keras gpu accuracy

modified Jan 9 at 15:21 Posi2 83

2

votes

3

answers

329

views

How to reproduce neural network training with keras

tensorflow keras

modified Jan 9 at 18:23 OverLordGoldDragon 141

6

votes

2

answers

279

views

Is word embedding a form of feature extraction?

comparison word-embedding feature-extraction

modified Dec 27 '19 at 20:43 nbro 11.1k

8

votes

3

answers

159

views

Why can neural networks generalize at all?

neural-networks machine-learning overfitting learning-theory generalization

modified Jan 4 at 21:42 jgleoj23 76

5

votes

1

answer

201

views

What is the mathematical definition of an activation function?

neural-networks deep-learning math definitions activation-function

modified Jan 10 at 13:19 nbro 11.1k

3

votes

2

answers

103

views

What's the function that SGD takes to calculate the gradient?

neural-networks deep-learning backpropagation loss-functions gradient-descent

modified Jan 15 at 13:42 nbro 11.1k

5

votes

2

answers

127

views

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

neural-networks deep-learning python math

modified 17 hours ago David Refaeli 277

3

votes

2

answers

83

views

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

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

answered 6 hours ago Ramedlaw Vocinnas 21

1

vote

1

answer

99

views

My idea for general AI [closed]

neural-networks agi

modified Jan 6 at 21:07 Michael Hearn 530

3

votes

2

answers

48

views

How to use LSTM to generate a paragraph

deep-learning long-short-term-memory sequence-modelling text-classification text-generation

modified Jan 3 at 11:06 Clement Hui 1,488

1

vote

1

answer

75

views

In which cases is the categorical cross-entropy better than the mean squared error?

machine-learning comparison loss-functions mean-squared-error categorical-crossentropy

modified Jan 20 at 18:31 nbro 11.1k

2

votes

2

answers

85

views

Why are traditional ML models still used over deep neural networks?

machine-learning deep-learning keras comparison

modified Jan 15 at 13:23 Michael Grogan 141

2

votes

1

answer

101

views

Do all neurons in a layer have the same activation function?

neural-networks activation-function hidden-layers

modified Dec 30 '19 at 0:38 lfgtm 123

2

votes

1

answer

70

views

List of currently available artificial general intelligence systems

definitions reference-request agi

modified Dec 28 '19 at 14:41 nbro 11.1k

3

votes

1

answer

54

views

How to create a fully connected(matrix) layer with vector input

convolutional-neural-networks

modified Jan 3 at 4:17 Stephen Philip 79

3

votes

1

answer

84

views

How to formalize learning in terms of information theory?

deep-learning convolutional-neural-networks cross-entropy

modified Jan 6 at 15:11 Barium Nitrate 51

2

votes

1

answer

64

views

What are the differences between TensorFlow and PyTorch?

tensorflow comparison software-evaluation pytorch

modified Jan 20 at 10:50 nbro 11.1k

4

votes

2

answers

56

views

Does summing up word vectors destroy their meaning?

neural-networks machine-learning deep-learning natural-language-processing text-classification

answered Jan 9 at 9:03 Ketil Malde 31

3

votes

1

answer

55

views

What is the intuition behind the TD(0) equation with average reward, and how is it derived?

reinforcement-learning actor-critic temporal-difference

modified Jan 1 at 14:03 nbro 11.1k

3

votes

1

answer

70

views

Why is the average reward plot for my reinforcement learning agent different than the usual plots?

machine-learning reinforcement-learning

modified Jan 14 at 13:53 nbro 11.1k

1

vote

1

answer

54

views

Can we calculate mean recall and precision

deep-learning accuracy

modified Jan 7 at 2:45 Miguel Saraiva 599

3

votes

0

answers

109

views

Speaker Identification / Recognition for less size audio files

generative-model data-science speech-recognition state-of-the-art

modified Jan 10 at 7:14 Ashish Johnson 1

0

votes

3

answers

51

views

How to correctly label images for multi-label classification?

classification datasets

answered Jan 14 at 18:00 NikoNyrh 101

2

votes

1

answer

64

views

What is the difference between Sutton's and Levine's REINFORCE algorithm?

reinforcement-learning comparison policy-gradients reinforce

modified Jan 8 at 20:54 nbro 11.1k

4

votes

2

answers

48

views

Is there any classifier that works best in general for NLP based projects?

machine-learning deep-learning natural-language-processing classification text-classification

modified Jan 4 at 15:52 Arnav Das 81

1

vote

1

answer

60

views

What is a cascaded convolutional neural network?

deep-learning convolutional-neural-networks computer-vision definitions papers

modified Jan 10 at 15:03 nbro 11.1k

3

votes

1

answer

77

views

What is the $\ell_{2, 1}$ norm?

machine-learning feature-selection regularization

answered Jan 3 at 19:08 Felipe Vieira 26

3

votes

1

answer

46

views

What is a “batch” in batch normalization?

neural-networks batch-normalization

answered Dec 27 '19 at 16:22 mshlis 1,695

6

votes

1

answer

46

views

How does the generator in GAN's work?

deep-learning generative-adversarial-networks

modified Jan 18 at 13:21 nbro 11.1k

1

vote

1

answer

46

views

How is back-propagation useful in neural networks?

neural-networks deep-learning backpropagation

answered Jan 18 at 18:11 Matias Valdenegro 146

3

votes

1

answer

58

views

Why Monte Carlo epsilon-soft approach cannot compute $\max Q(s,a)$?

reinforcement-learning q-learning monte-carlo

modified Jan 19 at 8:46 Neil Slater 10.6k

3

votes

1

answer

45

views

Is the Q value updated at every episode?

reinforcement-learning q-learning

answered Jan 6 at 16:05 Miguel Saraiva 599

3

votes

1

answer

42

views

What does the notation sup dist mean in distributional RL?

reinforcement-learning math notation

modified Jan 7 at 11:45 nbro 11.1k

2

votes

1

answer

68

views

What is the neuron-level math behind backpropagation for a neural network?

backpropagation math resource-request

answered Jan 9 at 1:01 Recessive 668

1

vote

1

answer

52

views

How many parameters are being optimised over in a simple CNN?

convolutional-neural-networks python keras gradient-descent

modified Dec 26 '19 at 20:32 Miguel Saraiva 599

1

vote

1

answer

31

views

What is “Computational Linguistics”?

machine-learning natural-language-processing terminology

modified 13 hours ago DukeZhou♦ 5,557

2

votes

1

answer

65

views

Why is a softmax used rather than dividing each activation by the sum?

neural-networks activation-function

answered Jan 2 at 10:57 Brale_ 1,176

3

votes

1

answer

39

views

How to describe an keras Model in a scientific report

machine-learning keras academia

modified Dec 30 '19 at 19:19 DukeZhou♦ 5,557

3

votes

1

answer

47

views

Can dropout layers not influence LSTM training?

neural-networks keras long-short-term-memory dropout regularization

modified Jan 7 at 14:00 Makintosz 636

4

votes

1

answer

58

views

Is it expected that adding an additional hidden layer to my 3-layer ANN reduces accuracy significantly?

image-recognition hidden-layers multilayer-perceptron c++

answered Jan 4 at 11:48 Clement Hui 1,488

2

votes

1

answer

73

views

+50

Solving a planning if finding the goal state is part of the problem

algorithm optimization problem-solving graph-theory

answered 10 hours ago maaartinus 379

2

votes

2

answers

44

views

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

neural-networks deep-learning tensorflow javascript

modified Jan 20 at 18:17 nbro 11.1k

2

votes

0

answers

72

views

Is NLP likely to be sufficiently solved in the next few years?

natural-language-processing

modified Jan 3 at 21:14 Ash 21

0

votes

1

answer

43

views

How is the loss value calculated in order to compute the gradient?

deep-learning gradient-descent

modified Dec 29 '19 at 18:57 nbro 11.1k

2

votes

0

answers

69

views

Is this a problem well suited for machine learning?

ai-design theory

modified Jan 7 at 16:38 user1282931 161

2

votes

1

answer

53

views

How to use AI for language recognition?

machine-learning natural-language-processing audio-processing speech-recognition

modified Jan 4 at 17:07 Tina J 735

5

votes

1

answer

41

views

What is the intuition behind TD($\lambda$)?

reinforcement-learning comparison monte-carlo temporal-difference

modified 2 days ago nbro 11.1k

Top Questions

Looking for more? Browse the complete list of questions, or popular tags. Help us answer unanswered questions.