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
2answers
58 views

Why some neural network models in the 1980s shown as circuit models

I am familiar with the currently popular neural network models that have weights and are trained with backpropagation and gradient descent. However, I came across a different type of neural network ...
1
vote
1answer
24 views

How is the variational lower bound for hard attention derived in Show, Attend and Tell

How is the jump from line 1 to line 2 done in equation 10 of Show, Attend and Tell? While we're at it, another thing that might be muddying the waters for me is that I'm not clear on what the sum is ...
0
votes
0answers
21 views

Do $V_\theta$ and $V_s$ represent partial or total derivatives in the paper “Learning Continuous Control Policies by Stochastic Value Gradients”?

I was reading up on the Stochastic Value Gradients paper by Heess et al. In the paper, they describe a recursive process to calculate path-wise derivatives via equations (3) and (4), at the bottom of ...
1
vote
0answers
27 views

What is a Hebbian linear classifier?

I was reading Deep Learning of Representations for Unsupervised and Transfer Learning, and they state the following: They have only a small number of unlabeled examples (4096) and very few labeled ...
6
votes
2answers
74 views

What does “semantic gap” mean?

I was reading DT-LET: Deep transfer learning by exploring where to transfer, and it contains the following: It should be noted direct use of labeled source domain data on a new scene of target domain ...
0
votes
0answers
58 views

Comparing heuristics in A* search and rescue operation

I was reading a research paper titled A Comparative Study of A-star Algorithms for Search and rescue in Perfect Maze (2011). I have some doubts regarding it: 1. The Evaluation Function of $\mathrm{A}^...
1
vote
2answers
66 views

In variational autoencoders, what does p(x|z) mean?

If $x \sim \mathcal{N}(\mu,\,\sigma^{2})$, then it is a continuous variable, and therefore $P(x) = 0$ for any x. One can only consider things like $P(x<X)$ to get a probability greater than 0. So ...
1
vote
0answers
17 views

Clonal operator in Immune Clonal Strategy

I was reading about Immune Clonal Strategy, specifically about Monoclonal operator from Immunity clonal strategies, and it goes as follows: Here $a_i $ is a point and $a_i = \{ x_1, x_2, \cdots, x_m \...
1
vote
0answers
22 views

What is the meaning of “Our current objective weights every token equally and lacks a notion of what is most important to predict” in the GPT-3 paper?

On page 34 of OpenAI's GPT-3, there is a sentence demonstrating the limitation of objective function: Our current objective weights every token equally and lacks a notion of what is most important to ...
2
votes
0answers
36 views

How many papers about AI / ML were published in the recent years?

I am trying to formulate an argument at work saying the disruption in AI/ML is very high and that it is hard to stay "state of the art". I would like to support that hypothesis by numbers. ...
1
vote
0answers
25 views

The MLP output of a neural network can be written as $\|x\|\|w_l\|\cos(\theta_l)$: why is the norm easier to maximize?

The MLP output of a neural network is a dot product between the weights and the input and therefore can be written as $\|x\|\|w_l\|\cos(\theta_l)$ (see this for more details), where $x$ is the input, $...
0
votes
1answer
19 views

How does high entropy targets relate to less variance of the gradient between training cases?

I've been trying to understand the Distilling the Knowledge in a Neural Network paper by Hinton et al. But I cannot fully understand this: When the soft targets have high entropy, they provide much ...
0
votes
0answers
52 views

How to evaluate a Genome in NEAT

I am trying to implement NEAT from scratch by going through the original NEAT paper. I implemented a Genome class which consists of a list of Node Genes and ...
4
votes
1answer
63 views

What is the relation between self-taught learning and transfer learning?

I am new to transfer learning and I start by reading A Survey on Transfer Learning, and it stated the following: according to different situations of labeled and unlabeled data in the source domain, ...
0
votes
1answer
32 views

K dimensional WL test in K-WL GCN

I am reading a paper on the K-WL GCN. I did not complete the paper yet but I just skimmed over it. There I am trying to understand the K-WL test (page 3 Weisfeiler-Leman Algorithm). I think my ...
1
vote
2answers
79 views

Bayesian Perceptron: How is it compatible to Bayes Theorem?

I found a very interesting paper on the internet that tries to apply Bayesian inference with a gradient-free online-learning approach: [Bayesian Perceptron: Bayesian Perceptron: Towards fully Bayesian ...
0
votes
1answer
56 views

Bayesian Perceptron: Why to marginalize over neuron's output instead of it's weights?

I found a very interesting paper on the internet that tries to apply Bayesian inference with a gradient-free online-learning approach: Bayesian Perceptron: Towards fully Bayesian Neural Networks. I ...
0
votes
0answers
22 views

How is the discounted maximum entropy objective obtained for soft-q-learning and SAC

In the soft q-learning paper, they provide an expression for the maximum entropy objective that takes discounting into account. My main question is: can someone explain how they incorporated ...
1
vote
1answer
19 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?

I am facing difficulty in understanding the bolded portion of the following statement from this paper GANs are defined by a min-max two-player game between a discriminative network $D_\Psi(x)$ and ...
0
votes
1answer
28 views

What to do with a GAN that trained well but got worse over time?

I am training a WGAN-GP network based on the following paper, though I am using a different dataset. Now, for the first ~ 60-70 epochs, my network trained really well, which I could see in the loss ...
1
vote
1answer
48 views

Is there a full and precise formulation of Theorem 1 in the Integrated Gradients paper?

Theorem 1 (page 5) in the paper about Integrated Gradients states that Integrated gradients is the unique path method that is symmetry-preserving. What I miss is A precise formulation of the ...
0
votes
0answers
10 views

Is there any method that combines temporal action proposals with multiple actions' classifiers?

I am trying to classify actions in untrimmed videos. These videos contain a very imbalanced set of actions (where the background class is the majority). I have previously tried frame-wise action ...
3
votes
0answers
28 views

What's up with Neural Stochastic Differential Equations from a practical standpoint?

I've spent a few days reading some of the new papers about Neural SDEs. For example, here is one from Tzen and Raginsky and here is one that came out simultaneously by Peluchetti and Favaro. There are ...
0
votes
0answers
28 views

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

I'm trying to understand 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 same ...
0
votes
0answers
31 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
29 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
48 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
91 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
35 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
27 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
41 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
21 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
23 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
56 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 ...
2
votes
1answer
139 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
23 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
66 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
16 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
46 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
53 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
339 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
27 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
73 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
15 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
77 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 ...

1
2 3 4 5