User hanugm

5 votes

1 answer

293 views

What does "statistical efficiency" mean in this context?

asked Apr 19, 2021 at 5:34

5 votes

2 answers

327 views

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

terminology word-embedding embeddings

asked May 29, 2021 at 7:11

4 votes

1 answer

192 views

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

reinforcement-learning math value-functions books expectation

asked May 10, 2021 at 3:17

4 votes

1 answer

4k views

Which tasks are called as downstream tasks?

natural-language-processing terminology

asked Jun 26, 2021 at 8:54

4 votes

1 answer

939 views

Is there a widely accepted definition of the width of a neural network?

neural-networks deep-learning terminology

asked Sep 22, 2021 at 1:07

4 votes

1 answer

107 views

What is the stride information of an image referring here?

deep-learning convolutional-neural-networks terminology image-processing stride

asked Nov 26, 2021 at 22:37

4 votes

2 answers

105 views

Can I apply reparametrization trick on "any" deep neural network?

neural-networks training autoencoders

asked Nov 16, 2021 at 22:45

4 votes

1 answer

79 views

Is there any relation between the recursive neural network and recurrent neural network?

comparison recurrent-neural-networks recursive-neural-network

asked Dec 17, 2021 at 10:17

3 votes

2 answers

109 views

Why should one focus on spectral operations as a computer vision researcher?

computer-vision academia spectral-analysis

asked Jan 20 at 0:41

3 votes

1 answer

41 views

Is there any variant of perceptron convergence algorithm that ensures uniqueness?

reference-request algorithm-request convergence perceptron

asked May 22 at 7:12

3 votes

2 answers

201 views

In layman terms, what does "attention" do in a transformer?

neural-networks papers transformer attention

asked Oct 19, 2021 at 12:05

3 votes

2 answers

422 views

When can I call an entity a hyperparameter?

machine-learning definitions hyper-parameters

asked Oct 29, 2021 at 3:51

3 votes

2 answers

178 views

Is there any difference between affine transformation and linear transformation?

neural-networks terminology pytorch linear-algebra

asked Jul 16, 2021 at 23:42

3 votes

1 answer

227 views

What exactly is an XPU?

terminology pytorch implementation resource-request hardware

asked Jul 20, 2021 at 22:33

3 votes

4 answers

898 views

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

machine-learning comparison math definitions models

asked Dec 30, 2020 at 7:32

3 votes

1 answer

154 views

How do AI researchers imagine higher dimensions?

research academia dimensionality-reduction data-visualization

asked Oct 9, 2020 at 2:23

3 votes

1 answer

215 views

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

machine-learning comparison probability-distribution maximum-likelihood

asked Jan 8, 2021 at 10:35

3 votes

1 answer

386 views

Where do the feature extraction and representation learning differ?

machine-learning comparison terminology feature-extraction representation-learning

asked May 28, 2021 at 2:09

3 votes

3 answers

907 views

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

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

asked Jun 16, 2021 at 23:06

3 votes

2 answers

119 views

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

natural-language-processing definitions books tf-idf logarithm

asked Jun 13, 2021 at 0:04

3 votes

1 answer

103 views

What are the necessary mathematical properties to be a loss function in gradient based optimizations?

deep-learning objective-functions math optimization gradient-descent

asked Jul 28, 2021 at 4:55

3 votes

2 answers

1k views

What is Lipschitz constraint and why it is enforced on discriminator?

training math generative-adversarial-networks discriminator

asked Jul 29, 2021 at 10:23

3 votes

1 answer

359 views

What is numerical stability?

neural-networks machine-learning terminology numerical-algorithms

asked Aug 3, 2021 at 13:40

3 votes

3 answers

88 views

What are the mathematical properties of natural exponential function that lead to its usefulness in artificial intelligence?

math

asked Aug 17, 2021 at 0:21

2 votes

3 answers

108 views

Is there any domain in machine learning that solves a problem by using only analytical algorithms?

machine-learning math linear-regression numerical-algorithms

asked Aug 16, 2021 at 22:33

2 votes

1 answer

104 views

Is there any way to train a neural network without using gradients?

neural-networks training reference-request stochastic-gradient-descent

asked Aug 18, 2021 at 14:45

2 votes

2 answers

113 views

Why does critical points and stationary points are used interchangeably?

terminology books derivative

asked Aug 20, 2021 at 23:37

2 votes

1 answer

77 views

Is there any inherent assumption of start and goal states in an MDP?

reinforcement-learning markov-decision-process state-spaces

asked Aug 9, 2021 at 2:55

2 votes

1 answer

102 views

Do researchers generally treat tensors just as mathematical objects with certain shape?

research data-visualization tensor

asked Aug 4, 2021 at 11:26

2 votes

1 answer

365 views

What exactly is a Parzen?

terminology definitions probability

asked Aug 2, 2021 at 0:06

Stack Exchange Network

current community

your communities

more stack exchange communities

286 Questions

What does "statistical efficiency" mean in this context?

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

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

Which tasks are called as downstream tasks?

Is there a widely accepted definition of the width of a neural network?

What is the stride information of an image referring here?

Can I apply reparametrization trick on "any" deep neural network?

Is there any relation between the recursive neural network and recurrent neural network?

Why should one focus on spectral operations as a computer vision researcher?

Is there any variant of perceptron convergence algorithm that ensures uniqueness?

In layman terms, what does "attention" do in a transformer?

When can I call an entity a hyperparameter?

Is there any difference between affine transformation and linear transformation?

What exactly is an XPU?

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

How do AI researchers imagine higher dimensions?

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

Where do the feature extraction and representation learning differ?

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

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

What are the necessary mathematical properties to be a loss function in gradient based optimizations?

What is Lipschitz constraint and why it is enforced on discriminator?

What is numerical stability?

What are the mathematical properties of natural exponential function that lead to its usefulness in artificial intelligence?

Is there any domain in machine learning that solves a problem by using only analytical algorithms?

Is there any way to train a neural network without using gradients?

Why does critical points and stationary points are used interchangeably?

Is there any inherent assumption of start and goal states in an MDP?

Do researchers generally treat tensors just as mathematical objects with certain shape?

What exactly is a Parzen?