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
0
votes
0answers
17 views

How to implement the deconv which is used in “Visualizing and Understanding Convolutional Networks”

I'm trying to understand how the deconv referenced in the paper Visualizing and Understanding Convolutional Networks The paper states (section 2, p. 3): the deconvnet uses transposed versions of the ...
0
votes
0answers
27 views

Are regret values in each block of MC external sampling stored in each node of the block we are traversing down (denoted by $\{Q_1,…, Q_n\}$)?

Everything I know about Monte Carlo counterfactual regret minimization (CFR) comes from the paper Monte Carlo Sampling for Regret Minimization in Extensive Games by Marc Lanctot et al. So, I will use ...
0
votes
1answer
28 views

Converting age and sex variables to a 64-unit dense layer

I am studying a preprint for my own learning (https://www.medrxiv.org/content/medrxiv/early/2020/04/27/2020.04.23.20067967.full.pdf) and I am befuddled by the following detail of the neural network ...
1
vote
0answers
44 views

BlackOut - ICLR 2016: need help understanding the cost function derivative

In the ICLR 2016 paper BlackOut: Speeding up Recurrent Neural Network Language Models with very Large Vocabularies, on page 3, for eq. 4: $$ J_{ml}^s(\theta) = log \ p_{\theta}(w_i | s) $$ They have ...
1
vote
1answer
59 views

How exactly is Monte Carlo counterfactual regret minimization with external sampling implemented?

I have read many papers, such as this or this, explaining how external sampling works, but I still don't understand how the algorithm works. I understand you divide $Q$, which is the set of all ...
1
vote
0answers
29 views

Is the framework provided by this paper for checking the constraints of AI systems really new?

The authors of this paper present a framework for checking the constraints of AI systems using formal argumentative logic between 2 agents: an interrogating agent and a suspect agent. The ...
2
votes
0answers
33 views

What is the paper that states that humans incorrectly trust the incorrect explanations of the AI?

I was reading a paper on the subject of explainable AI and interpretability, in particular the tendency of people (even experts) to excessively trusting explanations given by AI. In the intro the ...
0
votes
0answers
26 views

Understanding policies in helicopter control in the paper by Andrew Ng et al

I was going through this paper on helicopter flight control using reinforcement learning by Andrew Ng et al. It defines two policy classes to learn two policies, one for hovering the helicopter and ...
4
votes
0answers
35 views

Visualizing the Loss Landscape of Neural Nets: Meaning of the word 'filter'?

I found myself scratching my head when I read the following phrase in the paper Visualizing the Loss Landscape of Neural Nets: To remove this scaling effect, we plot loss functions using filter-wise ...
0
votes
0answers
18 views

How is the marginal likelihood of wide valleys higher than that of narrow valleys when optimizing a cost function?

I am reading the paper Entropy-sgd: Biasing gradient descent into wide valleys by Chaudhari et al. From what I understand, wide valleys tend to generalize better than sharp ones because they are ...
1
vote
0answers
18 views

Why does the relativistic discriminator increase the probability that generated data are real and decrease the probability that real data are real?

I was reading the ESRGAN whitepaper, where I came across this line: Relativistic discriminator [2] is developed not only to increase the probability that generated data are real but also to ...
0
votes
0answers
22 views

PPO: sampling next action vs picking the most probable action

According to the original Proximal Policy Optimization paper (PPO paper), we always sample an action from the actor distribution. According to the link The overall loss is calculated as $\text{loss} =...
2
votes
0answers
54 views

What is the dimensionality of these derivatives in the paper “Active Learning for Reward Estimation in Inverse Reinforcement Learning”?

I'm trying to implement in code part of the following paper: Active Learning for Reward Estimation in Inverse Reinforcement Learning. I'm specifically referring to section 2.3 of the paper. Let's ...
1
vote
1answer
54 views

What is the difference between out of distribution detection and anomaly detection?

I'm currently reading the paper Likelihood Ratios for Out-of-Distribution Detection, and it seems that their problem is very similar to the problem of anomaly detection. More precisely, given a neural ...
2
votes
0answers
21 views

Is it possible to ensure the convergence when training a RNN weight on its SVD decomposition?

I'm reading the following paper in which the author seems to do 2 things interesting: The hidden-to-hidden weight matrix of the RNN is SVD decomposed and train separately. Each orthogonal part of the ...
2
votes
1answer
62 views

How does replacing states with latent representations help RL agents?

I have seen many papers using autoencoders to replace images (states) with latent representations. Some of those methods have shown higher rewards using such techniques. However, I do not understand ...
1
vote
0answers
12 views

How are the parameters $\alpha_i$ of hard attention trained?

I have a question about Show, Attend and Tell: Neural Image CaptionGeneration with Visual Attention paper by Xu. The basic mechanism of stochastic hard attention is that each pixel of the input image ...
1
vote
0answers
14 views

How can an “architectural motif” be extracted from a trained MLP?

I am trying to reproduce the paper Synthetic Petri Dish: A novel surrogate model for Rapid Architecture Search. In the paper, the authors try to reduce the architecture of an MLP model trained on ...
1
vote
1answer
38 views

What is the smoothness assumption in SVMs?

In this research paper, we have the following claim the smoothness assumption that underlies many kernel methods such as Support Vector Machines (SVMs) does not hold for deep neural networks trained ...
3
votes
2answers
68 views

What does the parameter $y$ stand for in function $g(y,\mu,\sigma)$ related to REINFORCE algorithm?

I am wondering what the parameter $y$ in the function $g(y,\mu,\sigma)=\frac{1}{(2\pi)^{1/2}\sigma}e^{-(y-\mu)^{2/2\sigma^2}}$ stands for in Section 6 (page 14) of the paper introducing the REINFORCE ...
1
vote
1answer
49 views

Have I understood the loss function from the original U-Net paper correctly?

In the original U-Net paper, it is written The energy function is computed by a pixel-wise soft-max over the final feature map combined with the cross entropy loss function. ... $$ E=\sum_{\mathbf{x} ...
6
votes
1answer
331 views

How to express a fully connected neural network succintly using linear algebra?

I'm currently reading the paper Federated Learning with Matched Averaging (2020), where the authors claim: A basic fully connected (FC) NN can be formulated as: $\hat{y} = \sigma(xW_1)W_2$ [...] ...
1
vote
0answers
26 views

How to derive compact convex set K and its diameter D to program Accelegrad algorithm in practice?

Given the original paper (https://arxiv.org/pdf/1809.02864.pdf), I would like to implement the Accelegrad algorithm for which I report the pseudocode of the paper: In the pseudocode, the authors ...
5
votes
0answers
59 views

Wasserstein GAN: Implemention of Critic Loss Correct?

The WGAN paper concretely proposes Algorithm 1 (cf. page 8). Now, they also state what their loss for the critic and the generator is. When implementing the critic loss (so lines 5 and 6 of Algorithm ...
2
votes
0answers
45 views

How does the support vector machine constraint imply that sample selection bias will not systematically affect the output of the optimisation?

I am currently studying the paper Learning and Evaluating Classifiers under Sample Selection Bias by Bianca Zadrozny. In section 3.4. Support vector machines, the author says the following: 3.4. ...
1
vote
0answers
13 views

How to obtain the policy in the form of a finite-state controller from the value function vectors over the belief space of the POMDP?

I was reading this paper by Hansen. It says the following: A correspondence between vectors and one-step policy choices plays an important role in this interpretation of a policy. Each vector in $\...
3
votes
1answer
76 views

What is meant by “the number of examples is reduced”, and why is this the case?

I am currently studying the paper Learning and Evaluating Classifiers under Sample Selection Bias by Bianca Zadrozny. In section 3.2. Logistic Regression, the author says the following: 3.2. Logistic ...
4
votes
0answers
90 views

$\frac{P(x_1 \mid y, s = 1) \dots P(x_n \mid y, s = 1) P(y \mid s = 1)}{P(x \mid s = 1)}$ indicates that naive Bayes learners are global learners?

I am currently studying the paper Learning and Evaluating Classifiers under Sample Selection Bias by Bianca Zadrozny. In section 3. Learning under sample selection bias, the author says the following: ...
2
votes
1answer
55 views

What is different in each head of a multi-head attention mechanism?

I have a difficult time understanding the "multi-head" notion in the original transformer paper. What makes the learning in each head unique? Why doesn't the neural network learn the same ...
1
vote
1answer
27 views

Why is Adam trapped in bad/suspicious local optima after the first few updates?

In the paper On the Variance of the Adaptive Learning Rate and Beyond, in section 2, the authors write To further analyze this phenomenon, we visualize the histogram of the absolute value of ...
0
votes
0answers
49 views

What could be a good $\mathcal{R}$ dataset in the article “Old Photo Restoration via Deep Latent Space Translation”?

There are three domains in this article: Old Photo Restoration via Deep Latent Space Translation. The real old pictures noted by $\mathcal{R}$, the artificial old pictures noted by $\mathcal{X}$, and ...
1
vote
0answers
17 views

What is the intuition behind equations 10, 11 and 12 of the paper “Noise2Noise: Learning Image Restoration without Clean Data”?

Can anyone help me understand these functions described in the paper Noise2Noise: Learning Image Restoration without Clean Data I have read the portion A.4 in the appendix but need a more detailed and ...
1
vote
1answer
59 views

Why does each component of the tuple that represents an action have a categorical distribution in the TRPO paper?

I was going through the TRPO paper, and there was a line under Appendix D "Approximating Factored Policies with Neural Networks" in the last paragraph which I am unable to understand The ...
2
votes
1answer
26 views

Does this diagram represent several LSTMs, or one through several timesteps?

I'm trying to read this paper describing Google's LSTM architecture for machine translation. It features this diagram on page 4: I'm interested in the encoder block, on the left. Apparently, the pink ...
1
vote
0answers
24 views

How does Google's 2016 GNMT architecture work?

I'm trying to read this paper describing Google's LSTM architecture for machine translation from 2016. However, I'm getting stuck as certain things are described too vaguely for me. This is a picture ...
0
votes
1answer
64 views

What is the meaning of these equations in Noise2Noise paper?

I am trying to understand what is meant by following equations in the Noise2Noise paper by Nvidia. What is meant by the equation in this image? What is $\mathbb{E}_y\{y\}$? And how should I try to ...
3
votes
1answer
57 views

How is MuZero's second binary plane for chess defined?

From the MuZero paper (Appendix E, page 13): In chess, 8 planes are used to encode the action. The first one-hot plane encodes which position the piece was moved from. The next two planes encode ...
1
vote
0answers
35 views

In the MINE paper, why is $\hat{G}_B$ biased, and how does the exponential moving average reduce the bias?

While reading the Mutual Information Neural Estimation (MINE) paper [1] I came across section 3.2 Correcting the bias from the stochastic gradients. The proposed method requires the computation of the ...
0
votes
0answers
18 views

How does scheduled sampling for transformers work?

I was reading this paper which applies a modified version of the transformers for traffic forecasting. I am somewhat familiar with the transformer architecture and how it functions, but, in the paper, ...
0
votes
0answers
41 views

Is the “mlpconv” layer in the “Network in Network” paper computing $1 \times 1$ convolutions or not?

I am reading the Network in Network paper. This is the equation they introduce for their mlpconv layer (equation 2 in the paper, page 3): $$ \begin{aligned} f_{i, j,...
1
vote
0answers
88 views

SeqGAN - Policy gradient objective function interpretation

Could someone clear my doubt on the loss function used in SeqGAN paper . The paper uses policy gradient method to train the generator which is a recurrent neural network here. Have I interpreted the ...
0
votes
0answers
17 views

What BERT predicts when the token supposed to be masked is not masked?

I am reading the BERT paper. In the paper, they say that: Although this allows us to obtain a bidirec- tional pre-trained model, a downside is that we are creating a mismatch between pre-training and ...
2
votes
0answers
30 views

How are the lower and upper bound values of the moths determined in the Moth-Flame Optimization algorithm?

I am currently implementing the Moth-Flame Optimization (MFO) Algorithm, based on the paper: Moth-Flame Optimization Algorithm: A Novel Nature-inspired Heuristic Paradigm. To calculate the values of ...
1
vote
2answers
223 views

What are some alternatives to “Papers with Code”?

There are lots of research papers available that are worth reading. We can read papers easily, but the associated code (not necessarily the official one developed by the authors of the paper) is often ...
3
votes
0answers
49 views

Why is it necessary to divide the priority range according to the batch size in Prioritized Experience Replay?

According to DeepMinds's paper Prioritized Experience Replay (2016), specifically Appendix B.2.1 "Proportional prioritization" (p. 13), one should equally divide the priority range $[0, p_\...
1
vote
0answers
27 views

Why scaling down the parameter many times during training will help the learning speed be the same for all weights in Progressive GAN?

The title is one of the special things in Progressive GAN, a paper of the NVIDIA team. By using this method, they introduced that Our approach ensures that the dynamic range, and thus the learning ...
2
votes
1answer
88 views

What are proxy reward functions?

The understanding I have is that they somehow adjust the objective to make it easier to meet, without changing the reward function. ... the observed proxy reward function is the approximate solution ...
1
vote
1answer
69 views

What does $r : \mathcal{S} \times \mathcal{A} \rightarrow \mathbb{R}$ mean in the article Hindsight Experience Replay, section 2.1?

Taken from section 2.1 in the article: We consider the standard reinforcement learning formalism consisting of an agent interacting with an environment. To simplify the exposition we assume that the ...
2
votes
0answers
60 views

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

I am confused about the training part in AttnGan. If you observe page 3. There are two types of losses for generator network: one involving the Deep Attentional Multimodal Similarity Model (DAMSM) ...
1
vote
1answer
172 views

Are mult-adds and FLOPs equivalent?

I am comparing different CNN architectures for edge implementation. Some papers describing architectures refer to mult-adds, like the MobileNet V1 paper, where it is claimed that this net has 569M ...