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.
322
questions
1
vote
1
answer
37
views
In the Dropout paper, why would increasing the dropout increase the error rate if the capacity is constant?
In the original paper on dropout, in section 7.3.2, we see that while keeping $pn$ constant, we get a (test) error increase by decreasing retainment below 0.6. Why would that happen? If $pn$ is ...
- 11
0
votes
0
answers
19
views
How can I transform the LSTM output to an embedding matrix of actions?
Page 3 of the paper Feudal Networks for Hierarchical Reinforcement Learning describes producing an 'embedding matrix' $U$ of size $(|a| \times k)$ from the output of an LSTM, given a $(d \times 1)$ ...
- 1
0
votes
0
answers
31
views
YOLO v1 confidence score during inference
I am studying the paper of Yolo v1. For the training part, everything is clear to me.
I cannot understand how does the confidence works during the inference stage, since Pr(Object) and ground truth ...
1
vote
0
answers
50
views
Has anyone here tried to implement MADDPG for a different environment and succeeded?
Has anyone tried implementing the multi-agent RL algorithm MADDPG (I've linked the paper below)? The paper seems to have a good amount citations, and they do have their code on github. However, a few ...
- 111
0
votes
0
answers
42
views
Are there papers that do an empirical investigation on DRL hyperparameters?
I am looking for papers that perform a study on DRL hyper-parameters. This paper does a fantastic job of describing the hyperparameters for on-policy algorithms. It would be great to get similar ...
- 478
5
votes
2
answers
321
views
InstructGPT: What is the sigma in the loss function and why $\log(\cdot)$ is being used?
InstructGPT: What is the sigma in the loss function and why $\log(\cdot)$ is being used?
$$ \operatorname{loss}(\theta) = -\frac{1}{\binom{K}{2}}E_{(x,y_w,y_l)\sim D}[\log(\sigma(r_{\theta}(x, y_w) - ...
- 161
0
votes
0
answers
16
views
How to understand the definition of $\lambda_i$ used in the return estimator proposed in the paper "Human-level Atari 200x faster"?
I'm reading article called "Human-level Atari 200x faster"
Agent57 uses Retrace (Munos et al., 2016) to compute return estimates
from off-policy data, but we observed that it tends to cut ...
- 230
1
vote
1
answer
32
views
What does this bracket notation $\langle\phi(x),v\rangle$ mean?
I found it at the bottom of page 2 of the paper Intriguing properties of neural networks (2014), in the form of
$$\underset{x\in\mathcal{I}}{\mathrm{arg\,max}}\langle\phi(x),v\rangle$$
- 121
0
votes
1
answer
188
views
Are there Explainable GNN methods for node regression tasks?
I am wondering if there are gnn explainable methods for a regression task (e.g., traffic forecasting) where nodes have numerical features and the predicted output is a numerical value. Most of ...
2
votes
0
answers
33
views
Where does the proximal policy optimization objective's ratio term come from?
I will use the notation used in the proximal policy optimization paper.
What approximation is needed to arrive at the surrogate objective (equation (6) above) with the ratio $r_t(\theta)$?
Put ...
- 203
2
votes
1
answer
151
views
Why do activation functions in neural networks have to be non-polynomial to approximate any function?
Can someone give me the main idea of the paper Multilayer Feedforward Networks With a Nonpolynomial Activation Function Can Approximate Any Function? I'm having trouble understanding it.
- 31
1
vote
0
answers
12
views
Where exactly is permutation happening in equation 5 of the paper "Learning with Sets in Multiple Instance Regression Applied to Remote Sensing"?
I am reading the article Learning with Sets in Multiple Instance Regression Applied to Remote Sensing about creating an embedding which is order-invariant to inputs ($m_{l}$). They referred to order-...
- 23
1
vote
1
answer
36
views
What is the meaning of $ (I - \gamma P^{\pi})^{-1} \left[\frac{\mu(a|s)}{\hat \pi_{\beta}(a|s)} \right](s, a)$?
In Theorem 3.1 of the conservative q-learning paper, what is the meaning of
$$ (I - \gamma P^{\pi})^{-1} \left[\frac{\mu(a|s)}{\hat \pi_{\beta}(a|s)} \right](s, a)$$?
I thought $(I - \gamma P^{\pi})^{-...
- 78
0
votes
0
answers
7
views
Solutions for free-form bin packing?
I'm working on a solution for free-form bin packing and what I have found so far is
https://www.researchgate.net/publication/267165843_A_scanline-based_algorithm_for_the_2D_free-...
4
votes
0
answers
54
views
What exactly is non-delusional Q-learning?
Problems occur when we combine Q-learning with a function approximator.
What exactly is the delusional-bias and non-delusional Q-learning? I am talking about the neurIPS 18 best paper Non-delusional Q-...
- 171
1
vote
0
answers
54
views
How does having zero advantage help with identifiability?
I am reading the D3QN paper and they have the following paragraph -
Equation (7) is unidentifiable in the sense that given $Q$ we cannot recover $V$ and $A$ uniquely. To see this, add a constant to $...
- 478
0
votes
1
answer
253
views
Papers on Prompt Engineering
I am into AI in general and NLP in particular. Besides, I have a background in philosophy, and the new LLMs like GPT-3 seem to have exciting capabilities. I want to study prompt engineering (for ...
- 115
0
votes
1
answer
22
views
Is there any work done on topic agnostic binary topic classification?
In the recent preprint paper Tree-based Focused Web Crawling with
Reinforcement Learning a new model is introduced to classify web pages called KwBiLSTM.
The input to this model is a featurized ...
- 229
0
votes
0
answers
86
views
Exact definition of WRN-d-k (Wide ResNet)
I am a little confused about the WRN-d-k notation from Wide Residual Networks. To quote the paper,
In the rest of the paper we use the following notation: WRN-n-k denotes
a residual network that has ...
- 181
0
votes
0
answers
13
views
No question representation invlolved in the equation of a QA reader
I have read Dense passage retrieval for Open Domain Question Answering, and in the page 7 they define the probability that a span contains the answer as follows:
Equation $(5)$ defines an attention ...
- 361
0
votes
0
answers
456
views
In-batch negative training Improves the results
I have read Dense passage retrieval for Open Domain Question Answering, and in page 6 it talks about in-batch negative training, it states the following:
We find that using a similar
configuration (7 ...
- 361
0
votes
0
answers
21
views
Prototypical Network - Should I train my backbone or a separate embedder?
When I read the prototypical paper Prototypical Networks for Few-shot Learning, I understand in Eq. 1 that I should train $f_\phi$, which takes as input $x_i$, which is already an embedding of an ...
0
votes
1
answer
50
views
What do we mean by the notation $\mathbf{x}_{p} \in \mathbb{R}^{N \times\left(P^{2} \cdot C\right)}$?
I was going through this VIT paper, what will it look like in torch , if we are trying to write this expression.
- 101
0
votes
0
answers
15
views
How is the union bound being used?
I am trying to understand the assumption proof of Theorem 2(Page -$7$) in the paper "A Universal Law of Robustness via isoperimetry" by Bubeck and Sellke.
Inequality 1
\begin{align}
\mathbb{...
- 111
1
vote
0
answers
62
views
What are semantic word spaces in NLP?
In the abstract of this paper, it's written
Semantic word spaces have been very useful but cannot express the meaning of longer phrases in a principled way.
I would like to understand what semantic ...
- 121
2
votes
1
answer
267
views
In the MuZero paper, how does backprop in the MCTS account for the immediate reward from each edge?
On page 12 of this paper: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model, it describes how MCTS works for the MuZero algorithm. It states in equation 4 that during the 'backup' ...
- 23
0
votes
1
answer
1k
views
What is a "canonical space"?
I am reading the paper on 3D reconstruction, ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction, and I encountered the term "canonical space".
What is a "...
0
votes
0
answers
38
views
Why is the projection reasonable in C51 algorithm?
In this paper, there is an equation about the projection.
The author said
we project the sample Bellman update $\hat{T}Z_θ$ onto the support of $Z_θ$
Why is the original support reasonable? And why ...
- 3
0
votes
1
answer
71
views
Is the "Helvetica scenario" mentioned here related to Artificial Intelligence?
Consider the following sentence from the original GAN paper titled Generative Adversarial Nets
in particular, $G$ must not be trained too much without updating $D$, in order to avoid "the ...
- 3,481
2
votes
1
answer
51
views
How to decode P bits that represent a random weight generator?
So I've been tasked by my neural network professor at university to replicate the following research: Intelligent Breast Cancer Diagnosis Using Hybrid GA-ANN.
Each chromosome represents a possible net,...
- 21
4
votes
1
answer
165
views
What is the total number of actions and rewards count
Reading this two articles about Reinforcement Learning:
Deep Reinforcement Learning with Double Q-learning by Hado van Hasselt et al.
Human-level control through deep reinforcement learning by ...
- 143
0
votes
0
answers
18
views
Recursive Memory Optimized Gradient Graph Explained?
I'm reading the paper Training Deep Nets with Sublinear Memory Cost by Tianqi Chen, et. al. The paper is known for the $O(\sqrt n)$ memory cost to train a $n$-layer neural network.
My problem is ...
- 111
0
votes
1
answer
23
views
What is the right way to find the alphas in this equation?
In the Grad-CAM++ paper the following equation (7) is posed (written here without the relu function):
$$
Y^c =
\sum_k \Bigl( \Bigl\{ \sum_{a,b} \alpha_{ab}^{kc}
\cdot \frac{\partial Y^c}{\...
- 141
0
votes
1
answer
78
views
What is the correct partial derivative of $Y^c$ with respect to $A_{ij}^{kc}$?
I have a question about the Grad-CAM++ paper. I do not understand how the following equation (10) for the alphas is obtained:
$$
\alpha_{ij}^{kc} =
\frac{\frac{\partial^2 Y^c}{(\partial A_{ij}^k)^2}}
{...
- 141
2
votes
1
answer
146
views
What is a 'degenerate run' in evaluating model performance?
I've recently come across a paper that uses the term "degenerate run", but I'm not sure if I understand what it means. The idea is that when they report the average performance of running ...
- 121
1
vote
0
answers
91
views
What does "position" in "each position in the decoder" denote in the Transformer's original paper?
I am reading Attention is All You Need and I feel confused about the word "position" in this paper, by the way I'm not native English speaker which may cause my confusion which has confused ...
- 11
1
vote
0
answers
220
views
How are 4D cost volumes constructed for DL based stereo matching?
I read a paper on Stereo Matching using Pyramid Cost Volumes (paper link: Semantic Stereo Matching with Pyramid Cost Volumes). At some point, in the proposed architecture, after:
Feature extraction ...
- 11
0
votes
0
answers
27
views
Derivation in paper Deep Neural Networks as Gaussian processes in ICLR 2018
I am trying to understand the derivation of the main equation in the seminal paper titled Deep Neural Networks as Gaussian processes (in ICLR 2018). I have asked this question in https://math....
0
votes
0
answers
34
views
How does spatial pyramid pooling really work?
I went over the SPP paper (by Kaiming He) and understood in general that SPP can solve the fixed input size of the network problem (mainly due to the FC layer and not the CNN itself). Furthermore, the ...
- 1
1
vote
1
answer
224
views
What are the steps to derive the original GAN loss function from the generalized version?
I am trying to understand how the loss function from the original GAN paper
$$\min_{G} \max_{D} V(D, G)=\mathbb{E}_{\boldsymbol{x} \sim p_{\text {data }}(\boldsymbol{x})}[\log D(\boldsymbol{x})]+\...
- 13
0
votes
1
answer
256
views
When calculating the max in DQN, do I have to calculate the Q for every possible action for a particular state?
I'm trying to implement the DQN paper using python/pytorch for my needs (https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf). I'm studying the main algorithm:
I am a bit confused about the $\gamma* \max ...
0
votes
0
answers
22
views
Is there any sort of 'best practice' for giving the general public access to deep learning models to accompany academic papers?
Is there any sort of 'best practice' for giving the general public access to deep learning models to accompany academic papers?
1
vote
1
answer
49
views
Is the initial teacher model in the Noisy Student algorithm noised?
Reading through the paper on the Noisy Student algorithm, I have a quick question about how the initial teacher model is built.
In step 1 of the algorithm, the loss function is defined such that it ...
- 13
1
vote
1
answer
70
views
How is AI used in Internet of Things?
I would really appreciate it if someone would explain how AI is used in IoT. In the papers that I have found, half of the paper itself is about what IoT is and very few information about how AI is ...
- 19
0
votes
0
answers
57
views
How to reduce loss of Bi-LSTM handwriting recognition model?
I am currently training an bi-LSTM model which predicts the handwriting of an individual. I am hitting a current min loss of 1.2 and I think it is not a problem with the model because I copied a model ...
0
votes
1
answer
344
views
PPO advantage estimate - Why does advantage estimate have $r_t+\gamma V(s_{t+1})-V(s_t)$
So I've been looking at this formula for advantage estimate
\begin{equation}
\begin{aligned}
& \hat{A}_t = \delta_t + (\gamma \lambda)\delta_{t+1} + ... + (\gamma \lambda)^{T-t+1}\delta_{T-1}\\
&...
- 687
1
vote
0
answers
85
views
What do state features mean in the context of inverse RL?
I am reading Zeibart's Inverse RL paper, and it states -
The agent is assumed to be attempting to optimize some function that linearly maps the features of each state, $f_{sj} \in \mathbb{R}^k$, to a ...
- 478
1
vote
1
answer
67
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
1
answer
53
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 ...
- 37
2
votes
1
answer
3k
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.
...
- 183