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.

63 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
5
votes
1answer
74 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. ...
3
votes
0answers
42 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_\...
3
votes
0answers
141 views

Understanding the results of “Visualizing and Understanding Convolutional Networks”

I am trying to understand the results of the paper Visualizing and Understanding Convolutional Networks, in particular the following image: What are these 3x3 blocks and their 9 cells representing? ...
3
votes
0answers
45 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. ...
3
votes
1answer
92 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 ...
3
votes
1answer
72 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 ...
3
votes
1answer
345 views

What is the significance of this Stanford University “Financial Market Time Series Prediction with RNN's” paper?

Researchers at Stanford University released, in 2012, the paper Financial Market Time Series Prediction with Recurrent Neural Networks. It goes on to discuss how they used echo state networks to ...
2
votes
1answer
29 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 ...
2
votes
0answers
25 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 ...
2
votes
1answer
64 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 ...
2
votes
0answers
87 views

What is the memory complexity of the memory-efficient attention in Reformer?

When I read the paper, Reformer: The Efficient Transformer, I cannot get the same complexity of the memory-efficient method in Table 1 (p. 5), which summarizes time/memory complexity of scaled dot-...
2
votes
0answers
47 views

What is meant by “arranging the final features of CNN in a grid” and how to do it?

In the paper What You Get Is What You See: A Visual Markup Decompiler, the authors have proposed a method to extract the features from the CNN and then arrange those extracted features in a grid to ...
2
votes
0answers
58 views

What is a heatmap in the CornerNet paper?

I have been working on understanding how CornerNet works, but I couldn't figure out a few parts about the architecture. First, the authors mention that there are 3 distinct parts to be predicted as a ...
2
votes
0answers
25 views

Deriving hyperparameter updates in Online Interactive Collaborative Filtering

I've been going through "Online Interactive Collaborative Filtering Using Multi-Armed Bandit with Dependent Arms" by Wang et al. and am unable to understand how the update equations for the ...
2
votes
0answers
38 views

Are the final states not being updated in this $n$-step Q-Learning algorithm?

I am reading this paper and in algorithm 3 they describe an $n$-step Q-Learning algorithm. Below is the pseudo-code. From this pseudo-code, it looks as though the final tuples that they would ...
2
votes
0answers
49 views

How are the classical MDP and the object-oriented MDP views different?

I've been reading the attached paper - which aims to model entities in the world as objects, including the learning agent itself! To say the least, the goal is to navigate through what seems like a ...
2
votes
0answers
40 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
0answers
49 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 ...
2
votes
0answers
38 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 ...
2
votes
0answers
44 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....
2
votes
0answers
34 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 ...
2
votes
0answers
39 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 ...
2
votes
0answers
32 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 ...
2
votes
0answers
47 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 ...
2
votes
0answers
82 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 ...
2
votes
0answers
169 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
0answers
11 views

How do we stack two U-Nets to yield one final prediction?

I am trying to reproduce the model described in the paper DocUNet: Document Image Unwarping via A Stacked U-Net, i.e. stacking two U-Nets to yield one final prediction. The paper mentions that: ...
2
votes
1answer
102 views

How to perform back-propagation in Decoupled Neural Interfaces?

I am attempting to create a fully decoupled feed-forward neural network by using decoupled neural interfaces (DNIs) as explained in the paper Decoupled Neural Interfaces using Synthetic Gradients (...
1
vote
0answers
29 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 ...
1
vote
0answers
84 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 ...
1
vote
0answers
25 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 ...
1
vote
0answers
27 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
68 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 ...
1
vote
0answers
28 views

How to understand this NN architecture?

I was reading a paper Multi-Agent Reinforcement Learning for Adaptive User Association in Dynamic mmWave Networks and I was stuck understanding the deep neural network architecture that was used. The ...
1
vote
0answers
23 views

How do non-local neural networks relate to attention and self-attention?

I've been reading non-local neural networks as explained in the original paper. My understanding is that they solve the restrained reception of local filters. I see how they are different from ...
1
vote
0answers
76 views

How can a de-noising auto-encoder act as an anomaly detection model?

In some research papers, I have seen that, for training the autoencoders, instead of giving the non-anomalous input images, they add some anomalies to the normal input images, and train the auto-...
1
vote
0answers
77 views

Ways to keep up with the latest developments in Machine Learning and AI?

With over 100 papers published in the area of artificial intelligence, machine learning and their subfields every day (source), accounting for ~3% of all publications world wide per year (source) and ...
1
vote
0answers
24 views

What is the score used to visualize attention in this paper?

I'm reading this paper Global-Locally Self-Attentive Dialogue State Tracker and follow through the implementation published in GLAD. I was wondering if someone can clarify what variable or score is ...
1
vote
0answers
29 views

How are the coefficients of the Region of Interest being selected?

I was reading the following paper: Rl-Ncs: Reinforcement Learning Based Data-Driven Approach For Nonuniform Compressed Sensing, and my question is: how do they decide whether a signal is characterized ...
1
vote
0answers
34 views

Why can't neural networks be applied to preference learning problems?

In section 6.1 of the paper Neural Networks in Economics, the authors say this leads to the problem, that no risk can be formulated which shall be minimized by a Neural Network learning algorithm. ...
1
vote
0answers
50 views

What is a Hidden Markov Model - Artificial Neural Network (HMM-ANN)?

As far as I know, neural networks have hidden computational units and HMM has hidden states. Hidden Markov Models can be used to generate a language, that is, list elements from a family of strings. ...
1
vote
0answers
31 views

What do the authors of this paper mean by the bias term in this picture of a neural network implementation?

I am reading a paper implementing a deep deterministic policy gradient algorithm for portfolio management. My question is about a specific neural network implementation they depict in this picture (...
1
vote
0answers
26 views

How can transition models in RL be trained adversarially?

To give a little background, I've been reading the COBRA paper, and I've reached the section that talks about the exploration policy, in particular. We figure that a uniformly random policy won't do ...
1
vote
1answer
35 views

Why is this variable in equation 2 of the SQAIR paper a random vector of $n$ ones followed by a zero?

I've been reading the SQAIR paper lately, and the mathematics involved seems a bit complicated. Some background, about the paper: SQAIR stands for Sequential Attend, Infer, Repeat - the paper does ...
1
vote
0answers
23 views

Is the TD-residual defined for timesteps $t$ past the length of the episode?

Let $\mathcal{S}$ be the state-space in a reinforcement learning problem where rewards are in $\mathbb{R}$, and let $V:\mathcal{S} \to \mathbb{R}$ be an approximate value function. Following the GAE ...
1
vote
0answers
42 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 ...
1
vote
0answers
22 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 ...
1
vote
1answer
94 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 ...
1
vote
0answers
33 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} \...
1
vote
0answers
41 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 ...