User hanugm

5

votes

2

answers

279

views

Is an embedding a representation of a word or its meaning?

May 29 at 13:01 nbro♦ 27.4k

4

votes

1

answer

219

views

What does “statistical efficiency” mean in this context?

convolutional-neural-networks terminology books

Apr 19 at 11:34 nbro♦ 27.4k

1

4

votes

1

answer

176

views

How can a probability density value be used for the likelihood calculation?

machine-learning comparison probability-distribution maximum-likelihood probability-density

Jan 8 at 12:53 David Ireland 3,698

3

votes

2

answers

67

views

Why do we commonly use the $\log$ to squash frequencies?

natural-language-processing definitions books tf-idf logarithm

Jun 16 at 16:06 Aray Karjauv 376

3

votes

1

answer

35

views

Where do the feature extraction and representation learning differ?

machine-learning comparison terminology feature-extraction feature-learning

May 28 at 13:35 nbro♦ 27.4k

3

votes

1

answer

158

views

How is the state-value function expressed as a product of sums?

reinforcement-learning math value-functions books expectation

May 10 at 13:45 nbro♦ 27.4k

1

3

votes

0

answers

55

views

What are the purposes of pooling in CNNs?

convolutional-neural-networks pooling

Mar 16 at 10:42 nbro♦ 27.4k

3

votes

4

answers

509

views

What is the fundamental difference between an ML model and a function?

machine-learning comparison math definitions models

Mar 2 at 10:18 nbro♦ 27.4k

3

votes

1

answer

115

views

How do AI researchers imagine higher dimensions?

research academia dimensionality-reduction data-visualization

Oct 13 at 22:40 nbro♦ 27.4k

2

votes

1

answer

36

views

What is the meaning of “continuous” in a continuous bag-of-words model?

terminology books bag-of-words cbow

Jun 10 at 16:58 Oliver Mason 4,386

2

votes

1

answer

50

views

Is existence and uniqueness of state-value function at $\gamma < 1$ theoretical?

reinforcement-learning proofs value-functions books policy-evaluation

May 12 at 12:09 nbro♦ 27.4k

2

votes

0

answers

91

views

What is the purpose of the DAMSM loss for the generators in AttnGAN?

loss-functions papers generative-adversarial-networks attn-gan

Apr 5 at 6:37 hanugm 729

1

2

votes

1

answer

287

views

Is there any difference between ConvNet and CNN?

convolutional-neural-networks terminology

Feb 16 at 16:07 raghu 116

1

2

votes

2

answers

373

views

What is the need for so many filters in a CNN?

convolutional-neural-networks computer-vision keras filters convolutional-layers

Oct 15 at 21:18 nbro♦ 27.4k

1

vote

1

answer

40

views

In logistic regression, why is the binary cross-entropy loss function convex?

loss-functions optimization gradient-descent binary-classification cross-entropy

18h ago Abhijith S. Raj 1

1

vote

1

answer

31

views

What are the 'noisy factors' leading to overfitting?

machine-learning terminology overfitting books

Jun 18 at 14:19 nbro♦ 27.4k

1

vote

1

answer

40

views

How do very rare words tend to have very high PMI values?

natural-language-processing pointwise-mutual-information intuition

Jun 14 at 7:16 Oliver Mason 4,386

1

vote

1

answer

72

views

Is it okay to think of any dataset in artificial intelligence as a mathematical set?

datasets math definitions

Jun 10 at 6:15 hanugm 729

1

vote

1

answer

34

views

Is categorical encoding a type of word embedding?

comparison terminology word-embedding categorical-data one-hot-encoding

Jun 6 at 0:17 nbro♦ 27.4k

1

vote

0

answers

31

views

How do sparse word embeddings fail to capture synonymy?

natural-language-processing word-embedding sparse-word-embedding

Jun 4 at 14:32 nbro♦ 27.4k

1

vote

0

answers

24

views

Do literature uses (text) encoding and (word) embedding in a loose sense?

terminology word-embedding embeddings

Jun 2 at 3:31 hanugm 729

1

vote

0

answers

20

views

Is there any thumb rule on the cardinality of state space in order to use the parameterized function to estimate value functions?

reinforcement-learning deep-rl value-functions function-approximation state-spaces

May 11 at 9:29 hanugm 729

1

vote

1

answer

25

views

What is meant by “real-valued argument” in this context of the convolution operation?

deep-learning convolutional-neural-networks terminology convolution books

Apr 28 at 9:47 nbro♦ 27.4k

1

vote

1

answer

59

views

What is the reason for taking tuples as vectors rather than points?

machine-learning terminology datasets vectors

Mar 19 at 2:34 hanugm 729

1

vote

1

answer

23

views

Why does this paper say that the Nash-equilibrium of GAN is given by a discriminator which is 0 everywhere on the data distribution?

papers generative-adversarial-networks discriminator

Mar 18 at 12:48 CorruptedHeapScapeGoat 286

1

vote

1

answer

138

views

What is the definition of the hinge loss function?

neural-networks definitions support-vector-machine binary-classification hinge-loss

Feb 11 at 13:26 nbro♦ 27.4k

1

vote

1

answer

133

views

Confusion between function learned and the underlying distribution

terminology

Jan 4 at 8:16 Enigman 133

1

vote

1

answer

59

views

In the definition of the state-action value function, what is the random variable we take the expectation of?

reinforcement-learning q-learning value-functions notation random-variable

Oct 18 at 11:28 Neil Slater 18.9k

0

votes

0

answers

4

views

Self sufficient material(s) on maximum likelihood estimation

resource-request probability maximum-likelihood

30m ago hanugm 729

0

votes

2

answers

68

views

Book(s) for text embedding

natural-language-processing reference-request word-embedding books vector-semantics

1h ago hanugm 729

Stack Exchange Network

current community

your communities

more stack exchange communities

Next privilege

Next badge

39 Questions

Is an embedding a representation of a word or its meaning?

What does “statistical efficiency” mean in this context?

How can a probability density value be used for the likelihood calculation?

Why do we commonly use the $\log$ to squash frequencies?

Where do the feature extraction and representation learning differ?

How is the state-value function expressed as a product of sums?

What are the purposes of pooling in CNNs?

What is the fundamental difference between an ML model and a function?

How do AI researchers imagine higher dimensions?

What is the meaning of “continuous” in a continuous bag-of-words model?

Is existence and uniqueness of state-value function at $\gamma < 1$ theoretical?

What is the purpose of the DAMSM loss for the generators in AttnGAN?

Is there any difference between ConvNet and CNN?

What is the need for so many filters in a CNN?

In logistic regression, why is the binary cross-entropy loss function convex?

What are the 'noisy factors' leading to overfitting?

How do very rare words tend to have very high PMI values?

Is it okay to think of any dataset in artificial intelligence as a mathematical set?

Is categorical encoding a type of word embedding?

How do sparse word embeddings fail to capture synonymy?

Do literature uses (text) encoding and (word) embedding in a loose sense?

Is there any thumb rule on the cardinality of state space in order to use the parameterized function to estimate value functions?

What is meant by “real-valued argument” in this context of the convolution operation?

What is the reason for taking tuples as vectors rather than points?

Why does this paper say that the Nash-equilibrium of GAN is given by a discriminator which is 0 everywhere on the data distribution?

What is the definition of the hinge loss function?

Confusion between function learned and the underlying distribution

In the definition of the state-action value function, what is the random variable we take the expectation of?

Self sufficient material(s) on maximum likelihood estimation

Book(s) for text embedding