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.
332
questions
1
vote
0
answers
97
views
Question about the Conditioning Augmentation technique?
In the paper StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks, the goal is to convert text descriptions into images. The text encoder encodes the ...
- 51
0
votes
0
answers
32
views
Why is masked self attention necessary on GPT decoder
I'm currently reading the paper for the first GPT model and I'm confused about why masked self attention is necessary and I haven’t found any good answers online.
The consensus seems to be that we don'...
1
vote
0
answers
39
views
Are there neural networks that compute weights dynamically based on geometric attributes of neurons?
I am interested in exploring neural network architectures where the weights are not stored but are computed dynamically based on certain attributes or "dimensions" of the connected neurons.
...
1
vote
1
answer
104
views
How do Multimodal LLMs of 2023 score on the ARC benchmark (in 2020: 20% Accuracy)
Q: I wonder if anyone has tried to solve the ARC tasks with one of the state-of-the-art Multimodal LLMs?
Can LLMs that can process graphics input do the following?
(This question is not about the The ...
- 165
0
votes
0
answers
20
views
Training Diffusion Probabilistic Models
My question is in regards to the training process for Diffusion Probabilistic Models by Sohl-Dickenstein et. al. and also Ho et. al. and this blog post
For the derivation of the model log-likelihood ...
0
votes
0
answers
54
views
Question about feature matrix and notation in the paper Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning
Let me know if this is not the place for this question. I'll take it down happily if that's the case. Also, I emailed the authors, but it seems like I won't be getting a response, so that's why I am ...
- 242
0
votes
0
answers
48
views
Understanding the functionality of the switch in the latent diffusion models: Does conditioning information pass to both cross attention and $z_{T}$?
Consider the following diagram from the paper titled High-Resolution Image Synthesis with Latent Diffusion Models by Robin Rombach et. al.,
In the context of this diagram, I'm uncertain about the ...
- 3,612
0
votes
0
answers
24
views
Understanding the decreasing influence of text embedding in Text-to-Image diffusion models: A Mathematical perspective
I've been reading the paper titled eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers by Yogesh Balaji et. al. Consider the following excerpt from the abstract of the paper
...
- 3,612
0
votes
0
answers
8
views
Clarification regarding the training status of 'domain specific encoder' in stable diffusion
I am currently studying the paper titled High-Resolution Image Synthesis with Latent Diffusion Models by Robin Rombach et al. Specifically, I am focused on the section 3.3. Conditioning Mechanisms.
In ...
- 3,612
1
vote
1
answer
38
views
In-depth understanding of formulation and guidance mechanisms in Diffusion models
I've been reading a research paper titled High-Resolution Image Synthesis with Latent Diffusion Models by Robin Rombach et al. and came across an a concept related to diffusion models (DMs). In the ...
- 3,612
1
vote
0
answers
32
views
Can a Fully Connected Neural Network represent all Neural Networks of smaller size?
A fully connected Neural Network architecture can be characterized by a vector $\mathbf a = (a_0,a_1,\ldots,a_L)\in\mathbb N^{L+1}$ and an activation function $\sigma :\mathbb R\to\mathbb R$. In this ...
1
vote
0
answers
30
views
Meaning of a symbol in trace
I am reading this paper Not All Samples Are Created Equal: Deep Learning with Importance Sampling. In the paper there is a deviation shown below.
I can understand everything except the $V$ symbol in ...
- 49
0
votes
1
answer
337
views
In the original diffusion model paper, why do they sample the first step with the same loss?
In the original diffusion model paper by Sohl-Dickstein et al., they explain very little about calculating the loss and training and network to learn the diffusion process. They did publish a ...
- 101
0
votes
0
answers
8
views
Filter distribution of Latent variable models
In this paper https://arxiv.org/pdf/1907.00953.pdf, about stochastic latent variable models, the paper says "We use the
reparameterization trick to sample from the filtering distribution". I ...
- 15
0
votes
2
answers
83
views
BYOL: Why is there a prediction network in the online network but not in the target network?
In the BYOL paper, the following architecture is presented:
Why is a prediction network added to the online network, which is not present in the target network?
How are the online and target compared ...
- 2,083
0
votes
0
answers
44
views
Layer Questions regarding Bidirectional VAE (D3VAE)
I am currently trying to figure out how D3VAE are working, but I can't seem to understand the network architecture given. The paper can be found here:
https://openreview.net/pdf?id=rG0jm74xtx
The ...
0
votes
1
answer
58
views
What does crop size refer to in DeepLabv3 paper?
In the paper in which DeepLabv3 is presented, the authors are mentioning that:
"For atrous convolution with large rates to be effective, large
crop size is required; otherwise, the filter ...
- 11
3
votes
1
answer
362
views
Difference between dot product attention and "matrix attention"
As far as I know, attention was first introduced in Learning To Align And Translate.
There, the core mechanism which is able to disregard the sequence length, is a dynamically-built matrix, of shape ...
- 749
-1
votes
1
answer
152
views
Understanding self attention - How come there is no connection between different states?
During trying to understand transformers by reading Attention is all you need, I noticed the authors constantly refer to "self attention" without explaining it.
The original attention ...
- 749
1
vote
1
answer
56
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
26
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
49
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
108
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
45
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 ...
- 608
5
votes
2
answers
1k
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?
$$ \operatorname{loss}(\theta) = -\frac{1}{\binom{K}{2}}E_{(x,y_w,y_l)\sim D}[\log(\sigma(r_{\theta}(x, y_w) - ...
- 161
0
votes
0
answers
23
views
How to understand the definition of $\lambda_i$ used in the return estimator proposed in the paper "Human-level Atari 200x faster"?
I'm reading article called "Human-level Atari 200x faster"
Agent57 uses Retrace (Munos et al., 2016) to compute return estimates
from off-policy data, but we observed that it tends to cut ...
- 260
1
vote
1
answer
41
views
What does this bracket notation $\langle\phi(x),v\rangle$ mean?
I found it at the bottom of page 2 of the paper Intriguing properties of neural networks (2014), in the form of
$$\underset{x\in\mathcal{I}}{\mathrm{arg\,max}}\langle\phi(x),v\rangle$$
- 121
1
vote
1
answer
664
views
Are there Explainable GNN methods for node regression tasks?
I am wondering if there are gnn explainable methods for a regression task (e.g., traffic forecasting) where nodes have numerical features and the predicted output is a numerical value. Most of ...
- 11
2
votes
2
answers
133
views
Where does the proximal policy optimization objective's ratio term come from?
I will use the notation used in the proximal policy optimization paper.
What approximation is needed to arrive at the surrogate objective (equation (6) above) with the ratio $r_t(\theta)$?
Put ...
- 203
2
votes
1
answer
325
views
Why do activation functions in neural networks have to be non-polynomial to approximate any function?
Can someone give me the main idea of the paper Multilayer Feedforward Networks With a Nonpolynomial Activation Function Can Approximate Any Function? I'm having trouble understanding it.
- 31
1
vote
0
answers
14
views
Where exactly is permutation happening in equation 5 of the paper "Learning with Sets in Multiple Instance Regression Applied to Remote Sensing"?
I am reading the article Learning with Sets in Multiple Instance Regression Applied to Remote Sensing about creating an embedding which is order-invariant to inputs ($m_{l}$). They referred to order-...
- 43
1
vote
1
answer
54
views
What is the meaning of $ (I - \gamma P^{\pi})^{-1} \left[\frac{\mu(a|s)}{\hat \pi_{\beta}(a|s)} \right](s, a)$?
In Theorem 3.1 of the conservative q-learning paper, what is the meaning of
$$ (I - \gamma P^{\pi})^{-1} \left[\frac{\mu(a|s)}{\hat \pi_{\beta}(a|s)} \right](s, a)$$?
I thought $(I - \gamma P^{\pi})^{-...
- 118
5
votes
0
answers
69
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-...
- 183
1
vote
0
answers
65
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 $...
- 608
1
vote
1
answer
809
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 ...
- 123
0
votes
1
answer
32
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 ...
- 249
1
vote
0
answers
177
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 ...
- 271
0
votes
1
answer
950
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
1
answer
55
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
1
vote
0
answers
91
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
304
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
2k
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
1
answer
187
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 ...
- 3,612
2
votes
1
answer
69
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
259
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
1
answer
24
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
83
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
274
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
118
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
290
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