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
3
votes
0answers
23 views

How is the state-visitation frequency computed in “Maximum Entropy Inverse Reinforcement Learning”?

I am trying to understand the formulation of the maximum entropy Inverse RL method by Brian Ziebart. Particularly, I am stuck on how to understand the computation of state - visitation frequencies. ...
1
vote
1answer
34 views

What does equation in the “related work” section of the GAN paper mean?

I was going through the paper on GAN by Ian Goodfellow. Under the related work section, there is an equation. I cannot decipher the equation. Can anyone help me understand the meaning of the equation? ...
2
votes
0answers
21 views

Do I have to downsample the input and upsample the output of the neural network when implementing the NICE algorithm?

Consider that my input is an RGB image. The size of my image is $N\times N$. I'm trying to implement NICE algorithm presented by Dinh. The bijective function $f: \mathbb{R}^d \to \mathbb{R}^d$ maps $X$...
2
votes
1answer
39 views

Which work originally introduced gradient clipping?

The Deep Learning book mentions that it's been used for years but the oldest sources it mentions are from 2012: A simple type of solution has been in use by practitioners for many years: clipping ...
1
vote
0answers
25 views

Why does GAN loss converge to log(2) and not -log(2)?

In Goodfellow's paper, he says: Hence, by inspecting Eq. 4 at $D^*_G (\mathbf{x}) = \frac{1}{2}$, we find $C(G) = \log \frac{1}{2}+ \log \frac{1}{2} = − \log 4$. To see that this is the best ...
3
votes
1answer
35 views

Do all expert trajectories have the same starting state in apprenticeship learning?

In the apprenticeship learning algorithm described by Ng et al. in Apprenticeship Learning via Inverse Reinforcement Learning, they mention that expert trajectories come in the form of $\{s_0^i, s_1^i\...
1
vote
0answers
28 views

How can I get to a final output of shape $224 \times 224$, without FC layers, from a tensor of specific shape, in OpenPose?

I am approaching the implementation of the OpenPose algorithm for realtime human body pose estimation. According to the official paper OpenPose: Realtime Multi-Person 2D Pose Estimation using Part ...
1
vote
0answers
34 views

Recent algorithms for correcting mislabeled data using multilayer perceptrons

I am doing literature research on algorithms for correcting mislabeled data using multilayer perceptrons. Found an "old" paper An algorithm for correcting mislabeled data (2001) by Xinchuan Zeng et al....
3
votes
1answer
50 views

Are the labels updated during training in the algorithm presented in “An algorithm for correcting mislabeled data”?

I am trying to understand an algorithm for correcting mislabeled data in the paper An algorithm for correcting mislabeled data (2001) by Xinchuan Zeng et al. The authors are suggesting to update the ...
0
votes
1answer
28 views

How do you perform a gradient based adversarial attack on an SVM based model?

I have an SVM currently and want to perform a gradient based attack on it similar to FGSM discussed in Explaining And Harnessing Adversarial Examples. I am struggling to actually calculate the ...
1
vote
0answers
35 views

What AI conferences in Europe should I consider submitting papers to explaining the ongoing work on RefPerSys?

https://afia.asso.fr/journee-hommage-j-pitrat/ is a seminar on March 6th, 2020, in Paris (France, European Union), in honor of the late Jacques Pitrat, who advocated during all his professional life a ...
2
votes
0answers
20 views

How is the gradient with respect to weights derived in batch normalization?

This is a cross-post, as I didn't get any answers on Stats SE and I am hoping that it gets more attention here. At the bottom of page 2 of the paper L2 Regularization versus Batch and Weight ...
0
votes
2answers
165 views

Will AI always depend on models and thus approximations?

In section 3 of the paper The Limits of Correctness (1985) Brian Cantwell Smith writes When you design and build a computer system, you first formulate a model of the problem you want it to solve, ...
1
vote
0answers
33 views

Can GraphRNN be used with very large graphs?

In the GraphRNN paper, the authors only implement the algorithm up to a graph size of 2k nodes. Would this still work on much larger graphs (on the order of $10^7$)? Or would the computation just ...
2
votes
2answers
40 views

Is it feasible to use GAN for high-quality image synthesis other than human faces?

The famous Nvidia paper Progressive Growing of GANs for Improved Quality, Stability, and Variation, the GAN can generate hyperrealistic human faces. But, in the very same paper, images of other ...
1
vote
0answers
12 views

Scoring feature vector with Support Vector Machine

I am reading the R-CNN paper by Ross Girshick1 et al. (link) and I fail to understand how they do the inference. This is described in the section 2.2.Test-time Detection in the paper. I quote: At ...
2
votes
0answers
35 views

Why is this Monte Carlo approach scalable for a growing number of states variables and action variables?

I am reading a research paper on the formulation of MDP problems to ICU treatment decision making: Treatment Recommendation in Critical Care: A Scalable and Interpretable Approach in Partially ...
1
vote
1answer
121 views

What is a cascaded convolutional neural network?

For a project I am doing, I found the paper Face Alignment in Full Pose Range: A 3D Total Solution. It is using a cascaded convolutional neural network, but I wasn't able to find the original paper ...
2
votes
0answers
26 views

YOLO 9000 about Better Stronger

In this paper, YOLO has three features compared to YOLO v1. This question is about Better and Faster. In the Better section, there are many techniques such as Batch Norm, Anchor Box and so on. In the ...
4
votes
1answer
68 views

Are most things generally discovered because they work empirically and later justified mathematically, or vice-versa?

In the original GloVe paper, the authors discuss group theory when coming up with equation (4). Is it possible that the authors came up with this model, figured out it was good, and then later found ...
1
vote
1answer
35 views

What is “temporal depth”?

I need some explanation about the following paragraph (page 3) from the paper A Novel Approach for Robust Multi Human Action Detection and Recognition based on 3-Dimentional Convolutional Neural ...
1
vote
0answers
33 views

How can I get the predicted box in Faster R-CNN?

The RPN loss in Faster RCNN paper is $$ L({p_i}, {t_i}) = \frac{1}{N_{cls}} \sum_{i} L_{cls}(p_i,p_i^*) + \lambda \frac{1}{N_{reg}} \sum_i p_i^* L_{reg}(t_i, t_i^*) $$ For regression problems, we ...
2
votes
1answer
51 views

How GoogleNet actually deal with reducing overfitting?

Today I was going through a tutorial of Andrew Ng about Inception network. He said that GoogLeNet's hidden layers are also good in prediction and it had somehow a regularization effect, so it reduces ...
3
votes
1answer
62 views

Understanding proof of lemma 1 (policy improvement bound) of the “Trust Region Policy Optimization” paper

In the Trust Region Policy Optimization paper, in Lemma 1 of Appendix A, I did not quite understand the transition from (21) from (20). In going from (20) to (21), $A^\pi(s_t, a_t)$ is substituted ...
5
votes
1answer
247 views

What is the “semantic level”?

I am reading the paper Hierarchical Attention-Based Recurrent Highway Networks for Time Series Prediction (2018) by Yunzhe Tao et al. In this paper, they use several times the expression "semantic ...
0
votes
0answers
17 views

How is the general return-based off-policy equation derived?

I'm wondering how is the general return-based off-policy equation in Safe and efficient off-policy reinforcement learning derived $$\mathcal{R} Q(x, a):=Q(x, a)+\mathbb{E}_{\mu}\left[\sum_{t \geq 0} \...
4
votes
1answer
56 views

What is the meaning of the square brackets in ant colony optimization?

I'm studying the paper "Minimizing Total Tardiness on a Single Machine Using Ant Colony Optimization" which has proposed to use Ant colony optimization to SMTWTP. According to this paper: Each ...
4
votes
1answer
59 views

How does the network know which objects to track in the paper “Label-Free Supervision of Neural Networks with Physics and Domain Knowledge”?

I was reading the paper Label-Free Supervision of Neural Networks with Physics and Domain Knowledge, published at AAAI 2017, which won the best paper award. I understand the math and it makes sense. ...
1
vote
0answers
28 views

Why do both sine and cosine have been used in positional encoding in the transformer model?

The Transformer model proposed in "Attention Is All You Need" uses sinusoid functions to do the positional encoding. Why have both sine and cosine been used? And why do we need to separate the odd ...
3
votes
1answer
58 views

What is a non-starving policy in reinforcement learning?

In the paper, Eligibility Traces for off-Policy Policy Evaluation (2010), by Doina Precup et al., mentioned the term "non-starving" many times. The specific use of the term was like "non-starving ...
1
vote
0answers
27 views

Reference request: one-hot encoding outperforming random orthogonal encoding

I experimented with a CNN operating on texts encoded as sequences of character vectors, where characters are encoded as one-hot vectors in one embedding and as random unit length pairwise orthogonal ...
2
votes
0answers
38 views

What is the difference between Squeeze-and-excite and bottleneck modules from Mobilenet v2?

Squezee-and-excite networks introduced SE blocks, while MobileNet v2 introduced linear bottlenecks. What is the effective difference between these two concepts? Is it only implementation (depth-wise ...
3
votes
1answer
59 views

Is unsupervised disentanglement really impossible?

In Locatello et al's Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations he claims to prove unsupervised disentanglement is impossible. His entire claim is ...
1
vote
1answer
180 views

What is an identity recurrent neural network?

What is an identity recurrent neural network (IRNN)? What is the difference between an IRNN and RNN?
3
votes
1answer
47 views

How are the observations stored in the RNN that encodes the state?

I am a bit confused about observations in RL systems which use RNN to encode the state. I read a few papers like this and this. If I were to use a sequence of raw observations (or features) as an ...
4
votes
1answer
255 views

What is the meaning of “stationarity of statistics” and “locality of pixel dependencies”?

I'm reading the ImageNet Classification with Deep Convolutional Neural Networks paper by Krizhevsky et al, and came across these lines in the Intro paragraph: Their (convolutional neural networks') ...
0
votes
0answers
15 views

Derivation for Value Iteration of CVaR

I am reading a paper named Risk-sensitive and Robust Decision-making: a CVaR Optimization Approach. In appendix A.3 they provide a proof for their Theorem $4$. The $n=1$ case for equation (11) is ...
1
vote
1answer
64 views

Understanding the reconstruction loss in the paper “Anomaly Detection using Deep Learning based Image Completion”

I would like to implement the approach represented in this paper. Here they used following reconstruction loss: $$ L(X)= \frac{\lambda \cdot || M \odot (X - F(\overline{M} \odot X)) ||_{1} + (1 - \...
2
votes
1answer
48 views

What is “dense” in DensePose?

I've recently come across an amazing work for human pose estimation: DensePose: Dense Human Pose Estimation In The Wild by Facebook. In this work, they have tackled the task of dense human pose ...
2
votes
0answers
73 views

Infinite horizon in Reinforcement Learning

I read this article: "Towards Autonomous Data Ferry Route Design through Reinforcement Learning" by Daniel Henkel and Timothy X Brown. It specifies an infinite horizon problem where they use as a ...
5
votes
1answer
115 views

Are the ideas in the paper “Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour” novel?

In the paper Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour, the authors seem to be presenting a black box method of testing. Are these ideas really new? Weren't these ...
4
votes
1answer
121 views

Name of paper for encoding/representing XY coordinates in deep learning

It this podcast between Oriol Vinyals and Lex Friedman: https://youtu.be/Kedt2or9xlo?t=1769, at 29:29, Oriol Vinyals refers to a paper: If you look at research in computer vision where it makes a ...
1
vote
1answer
60 views

Understanding how the loss was calculated for the SQuAD task in BERT paper

In the BERT paper, section 4.2 covers the SQuAD training. From my understanding, there are two extra parameters trained, they are two vectors with the same dimension as the hidden size, so the same ...
1
vote
1answer
43 views

IQN bellman target: using Z vs using Q

IQN paper (https://arxiv.org/abs/1806.06923) uses distributional bellman target: $$ \delta^{\tau,\tau'}_t = r_t + \gamma Z_{\tau'}(x_{t+1}, \pi_{\beta}(x_{t+1})) - Z_{\tau}(x_t, a_t) $$ And optimizes: ...
3
votes
2answers
60 views

Why is the max a non-expansive operator?

In certain reinforcement learning (RL) proofs, the operators involved are assumed to be non-expansive. For example, on page 6 of the paper Generalized Markov Decision Processes: Dynamic-programming ...
2
votes
0answers
120 views

Why does the BERT encoder have an intermediate layer between the attention and neural network layers with a bigger output?

I am reading the BERT paper BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. As I look at the attention mechanism, I don't understand why in the BERT encoder we have ...
2
votes
1answer
36 views

How could we estimate the square footage of a room from an image?

I wonder if it would be possible to know the size of a room using image, I don't see anything about this subject, do you have some idea how it could be done?
3
votes
1answer
109 views

How is equation 8 derived in the paper “Self-critical sequence training for image captioning”?

In the paper "Self-critical sequence training for image captioning", on page 3, they define the loss function (of the parameters $\theta$) of an image captioning system as the negative expected reward ...
3
votes
2answers
606 views

What is a bad local minimum in machine learning?

What is "bad local minima"? The following papers all mention this expression. Eliminating all bad Local Minima from Loss Landscapes without even adding an Extra Unit limination of All Bad Local ...
1
vote
1answer
647 views

Why are there transition layers in DenseNet?

The DenseNet architecture can be summarizde with this figure: Why there are transition layers between each block? In the papers, they justify the use of transition layers as follow : The ...