Questions tagged [papers]

For questions related to artificial intelligence research papers. So, you should use this tag if you want someone to clarify something in a research paper.

Filter by
Sorted by
Tagged with
1
vote
1answer
41 views

What does the complexity equation constitute exactly in “Why Should I Trust You?” LIME paper

I've recently been reading this paper on LIME, an algorithm to interpret ANY machine learning model. I encountered this equation (in red) on page 4 and have just been having a hard time deciphering ...
0
votes
1answer
30 views

Does "number of actions" refer to the number of actions taken or size of the action space?

In the original DDQN article (https://arxiv.org/pdf/1509.06461.pdf,) the phrase "number of actions" is used twice; First, in the following context: Secondly in Theorem 1. I have a hard ...
0
votes
0answers
29 views

How to use EfficientDet for semantic segmentation?

In the EfficientDet paper, section 5.2. 5.2. EfficientDet for Semantic Segmentation, the authors say we modify our EfficientDet model to keep feature level $\{P2, P3, ..., P7\}$ in BiFPN, but only ...
0
votes
0answers
22 views

Is smoothing wrong in temporal predictions?

I found this paper from 2003 about predicting Forex rates: Using Recurrent Neural Networks To Forecasting of Forex. At the end of page 11, they say The network we built had two inputs and one output. ...
0
votes
0answers
25 views

What are the "two new constraints" that the authors of the "TeEther" paper are referring to?

Smart contracts (SC) are programs developed for Ethereum Blockchain initially. They are used for transferring Ether and subsequently can be applied in place of Banking transactions and credit cards. ...
1
vote
1answer
39 views

Does higher FLOPS mean higher throughput?

I understand that FLOPS means floating-point operations per second, and throughput is the number of inputs (for example, images) per second. If a model has higher FLOPS, it means it performs faster. ...
1
vote
0answers
25 views

Generative systems based on Schmidhuber's compression framework

In Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes ...
0
votes
1answer
26 views

What is the meaning of the shaded area in the reinforcement learning literature graphs?

In most of the reinforcement learning literature, I see that there is a shaded area in the graphs. I couldn't understand what it exactly represents? For example, from the A3C paper: Or another ...
6
votes
0answers
57 views

How can a neural network distinguish a rotated 6 and 9 digits?

Rotated MNIST is a popular dataset for benchmarking models equivariant to rotations on $\mathbb{R}^2$, described by $SO(2)$ group or its discrete subgroups like $\mathbb{Z}^{n}$: Group equivariant ...
0
votes
0answers
11 views

How to compute an AUROC score using the Mahalanobis distance?

I was reading this paper: A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks. The core idea is, given a test sample $x$, and a set of classes $C$, to compute ...
1
vote
1answer
44 views

Do we use two distinct layers to compute the mean and variance of a Gaussian encoder/decoder in the VAE?

I am looking at appendix C of the VAE paper: It says: C.1 Bernoulli MLP as decoder In this case let $p_{\boldsymbol{\theta}}(\mathbf{x} \mid \mathbf{z})$ be a multivariate Bernoulli whose ...
2
votes
3answers
116 views

Are the authors of the VAE paper writing the PDFs as a function of the random variables?

Usually, I see the conventions: discrete random variable is denoted as $X$, the pmf is written as $P(X=x)$ or $p(X=x)$ or $p_{X}(x)$ or $p(x)$, where $x$ is an instance of $X$ a continuous random ...
4
votes
2answers
396 views

How should I read a deep learning paper?

I have a background in mathematics and I am accustomed to reading papers with lemma and proofs. When I see a deep learning paper, they seem to be of practical nature. How can I improve my reading and ...
0
votes
1answer
31 views

Which is more popular/common way of representing a gradient in AI community: as a row or column vector?

Consider the following remark about writing gradients from the chapter named Vector Calculus from the test book titled Mathematics for Machine Learning by Marc Peter Deisenroth et al. Remark (...
1
vote
1answer
22 views

Does Seq2Seq decoder take a special vector or the weights of the last encoder cell as an output?

I'm reading Sequence to Sequence Learning with Neural Networks and there's a thing that I couldn't quite grasp. Paper says the encoder outputs a vector to be fed to the decoder. More precisely Our ...
1
vote
0answers
93 views

Where do the characteristics of self-attention come into play in Linformer's proof that self-attention is low rank?

In Linformer's proof that self-attention is low rank in their paper, I don't see how it doesn't generalize to every matrix. They don't utilize any specifics of self-attention (the entire proof feels ...
1
vote
0answers
85 views

Why does the number of input tokens to an LSTM have an impact on the convergence of Integrated Gradients?

Background I am computing the attribution scores for a simple LSTM model using Integrated Gradients. This method defines the contribution of a feature to a model prediction by integrating over the ...
3
votes
1answer
72 views

Why exactly was previously believed that the deterministic policy gradient did not exist?

I'm reading the paper Deterministic Policy Gradient Algorithms, David Silver et al. First of all, in the introduction, the author says that It was previously believed that the deterministic policy ...
1
vote
1answer
87 views

How is the VAE related to the Autoencoding Variational Bayes (AEVB) algorithm?

I am familiar with the variational autoencoder, but not totally clear on what exactly the AEVB is. In the original VAE paper (by Kingma and Welling), he uses both the terms variational autoencoder and ...
0
votes
0answers
78 views

Why is the Graph Isomorphism Network powerful?

I am reading a paper known as GIN, How powerful are graph neural networks?, Xu et al. 2019 The paper, Lemma 5 and Corollary 6, introduces Graph Isomorphism Network (GIN). In Lemma 5, Moreover, any ...
1
vote
1answer
126 views

What is a filter in the context of graph convolutional networks?

In Section 2.1 of the research paper titled Semi-Supervised Classification with Graph Convolutional Networks by Thomas N. Kipf et al., Spectral convolution on graphs defined as The multiplication of ...
1
vote
1answer
100 views

How does the VAE learn a joint distribution?

I found the following paragraph from An Introduction to Variational Autoencoders sounds relevant, but I am not fully understanding it. A VAE learns stochastic mappings between an observed $\mathbf{x}$...
1
vote
1answer
68 views

How are GCN doing semi-supervised learning?

In Semi-Supervised Classification with Graph Convolutional Networks, the authors say that GCN is an approach for semi-supervised learning (SSL). But a GCN is making predictions using only the graph ...
0
votes
0answers
52 views

In this paper, how does scaling the filter instead of the image generate saliency maps of the same size and resolution as the input image?

In this paper, in section 3.1, the authors state Scaling the filter instead of the image allows the generation of saliency maps of the same size and resolution as the input image. How is this ...
2
votes
2answers
131 views

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

I heard from many people about the paper titled Attention Is All You Need by Ashish Vaswani et al. What actually does the "attention" do in simple terms? Is it a function, property, or some ...
0
votes
0answers
89 views

Understanding gumbel-softmax backpropagation in Wav2Vec papers

I'm studying the series of Wav2Vec papers, in particular, the vq-wav2vec and wav2vec 2.0, and have a problem understanding some details about the quantization procedure. The broader context is this: ...
0
votes
0answers
37 views

Bert vs Sentence-Bert

I read a paper about Rumor detection and they used BERT as an unsupervised language representation, fine-tuning it using a small dataset, and combining it with a supervised learning model to provide ...
0
votes
0answers
16 views

Why does conditioning neural network function on adjacency matrix of graph allow for distribution of gradient information from the supervised loss?

I was reading the following paper here and had a question about the paragraph on page 1 (in the introduction). The equation being referred to is: $$ \mathcal{L} = \mathcal{L}_0 + \lambda \mathcal{L}_{\...
0
votes
1answer
124 views

In this paper, if region $R_{2}$ moves in a sliding window manner, won't the saliency map have a smaller size than the original image?

In the paper Salient Region Detection and Segmentation, I have a question pertaining to section 3 on the convolution-like operation being performed. I had already asked a few questions about the paper ...
1
vote
1answer
30 views

What is meant by "spatial encoding" in the context of convolutional neural networks?

Consider the following excerpt from the abstract of the research paper titled Squeeze-and-Excitation networks by Jie Hu et al. Convolutional neural networks are built upon the convolution operation, ...
0
votes
0answers
85 views

Discrepencies between the TimeGan paper and the code?

I recently read the paper Time-Series Generative Neural Networks and found the results that they reported quite promising (https://proceedings.neurips.cc/paper/2019/file/...
1
vote
0answers
12 views

Why actual mapping is called as unreferenced mapping in this context of residual framework?

Consider the following statements from the research paper titled Deep Residual Learning for Image Recognition by Kaiming He et al. #1: We explicitly reformulate the layers as learning residual ...
1
vote
1answer
76 views

What is the derivative of equation 1 in the paper "Conservative Q-Learning for Offline Reinforcement Learning"?

I am looking at the paper Conservative Q-Learning for Offline Reinforcement Learning, but I'm not sure how they proved theorem 3.1. Here is a screenshot of theorem 3.1. In the proof of theorem 3.1 ...
1
vote
2answers
40 views

Why do the authors of the T5 paper say that the "architectural changes are orthogonal to the experimental factors"?

Here's a quote from the T5 paper (T5 stands for "Text-to-Text Transfer Transformer") titled Exploring the Limits of Transfer Learning with a Unified Text-...
1
vote
0answers
47 views

What is the confusion loss for adversarial learning?

What is the confusion loss used in domain adaptation (DA) for adversarial learning/GANs? See this paper. Two domains: $s$: source domain $t$: target domain Generator/Discriminator setting: $M_s:x_s\...
0
votes
0answers
63 views

How does Chebyshev approximation of spectral convolution work?

I was reading the following paper: here. In it, it talks about spectral graph convolutions and says: We consider spectral convolutions on graphs defined as the multiplication of a signal $x \in R^N$ (...
1
vote
1answer
33 views

Why does Q-function training not query the Q-function value at unobserved states?

In the paper Conservative Q-Learning for Offline Reinforcement Learning, it is stated (section 3.1, page 3) that standard Q-function training does not query the Q-function value at unobserved states, ...
0
votes
0answers
23 views

How did authors ensure that critical points do exist in GAN?

Using an MLP as a generator introduces multiple critical points in parameter space. You can read this excerpt from the research paper titled Generative Adversarial Nets by Ian J. Goodfellow et al. In ...
0
votes
1answer
43 views

Why disentangling the features of variation in representation?

Consider the following excerpt from abstract of the research paper titled Better Mixing via Deep Representations by Yoshua Bengio et al. It has been hypothesized, ...
1
vote
0answers
20 views

Is the following a typo or am I understanding wrongly regarding discriminator?

Consider the following paragraph from the section 3: Background of the research paper titled Generative Adversarial Text to Image Synthesis by Scott Reed et al. ...
1
vote
1answer
41 views

Why does $I_N + D^{-\frac{1}{2}}AD^{-\frac{1}{2}}$ have eigenvalues in the range [0, 2]?

In Semi-supervised classification with Graph Convolutional Networks, I am unable to understand a few things. Given an undirected graph having adjacency matrix $A$, degree matrix $D_{ii} = \sum_j A_{...
0
votes
1answer
34 views

Where can I access this research paper on Frechet distance score?

Frechet Inception Distance is a metric that calculates the distance between feature vectors calculated for real and generated images. It is used in evaluations how good the generated images are. ...
1
vote
1answer
27 views

Bag of Tricks: n-grams as additional features?

I've been playing with PyTorch's nn.EmbeddingBag for sentence classification for about a month. I've been doing some feature engineering, playing with different ...
0
votes
1answer
93 views

What is the difference between a vision transformer and image-based relational learning?

I am trying to figure out the difference between the architecture used in this and this paper. It looks like both used multi-headed self-attention and therefore should be the same in principle.
2
votes
1answer
48 views

How is this statement from a TensorFlow implementation of a certain KL-divergence formula related to the corresponding formula?

I am trying to understand a certain KL-divergence formula (which can be found on page 6 of the paper Evidential Deep Learning to Quantify Classification Uncertainty) and found a TensorFlow ...
2
votes
1answer
53 views

What does it mean by strong or sufficient gradient for training in this context?

It has been mentioned in the research paper titled Generative Adversarial Nets that generator need to maximize the function $\log D(G(z))$ instead of minimizing $\log(1 −D(G(z)))$ since the former ...
0
votes
0answers
32 views

Why is the proof of convergence in the GAN paper not applicable practically?

This question is about generative adversarial networks and restricted to the research paper titled Generative Adversarial Nets. If I select a particular architecture of MLP as a generator and trained ...
1
vote
1answer
53 views

What is meant by "well-behaved gradient" in this context?

Consider the following statement (from the paper Generative Adversarial Nets) about the success of discriminative models So far, the most striking successes in deep learning have involved ...
2
votes
1answer
61 views

Why is the exponential loss used in this case?

I am reading the paper Tracking-by-Segmentation With Online Gradient Boosting Decision Tree. In Section 2.1, the paper says Given training examples, $\left\{\left(\mathbf{x}_{i}, y_{i}\right) \mid \...
1
vote
0answers
43 views

Computing the mean attention distance for ViT

Recently I came across the paper that introduces the Vision Transformer (ViT) "AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE". The thing I don't really ...

1
2 3 4 5 6