All Questions

Filter by
Sorted by
Tagged with
0
votes
0answers
38 views

MCTS: What if all children of a node are terminal?

If all children Nodes of the selected node are terminal in the selection phase - you obviously run into a problem. So how do I prevent a Node to be selected that only has terminal children?
1
vote
0answers
33 views

Are monotonically increasing functions easier to learn?

A monotonically increasing function is a function that as x gets bigger so does its output. So, if plotted, it will never go down. Although the outputs might stay constant. Logically this seems like ...
2
votes
1answer
62 views

What is $ \nabla_{\theta_{k-1}} \theta_{k}$ in the context of MAML?

I am attempting to fully understand the explicit derivation and computation of the Hessian and how it is used in MAML. I came across this blog: https://lilianweng.github.io/lil-log/2018/11/30/meta-...
1
vote
2answers
100 views

How to extract parameters from a text using AI/NLP

lets say I have three texts: "make a heading that says hello word" "make a heading of hello world" "create heading consist of hello world" How can I fetch those groups ...
2
votes
0answers
82 views

Offline/Batch Reinforcement Learning: when to stop training and what agent to select

Context: My team and I are working on a RL problem for a specific application. We have data collected from user interactions (states, actions, rewards, etc.). It is too costly for us to emulate agents....
2
votes
0answers
29 views

Why does batch norm standardize with sample mean/variance, when it also learns parameters to scale the mean/variance?

Batch norm is a normalizing layer that is shown to help deep networks learn faster and with higher generalization accuracy. It normalizes the activations of the previous layer to a mean $\beta$ and ...
5
votes
1answer
166 views

What are the advantages of RL with actor-critic methods over actor-only methods?

In general, what are the advantages of RL with actor-critic methods over actor-only (or policy-based) methods? This is not a comparison with the Q-learning series, but probably a method of learning ...
0
votes
0answers
28 views

ML method for detecting which individuals are best predicted by the features

Broad question to help in finding an appropriate method. So I have a given feature set of (DNA/genetic) predictors and a group of individuals which are either cases or controls for diseaseX. While I ...
0
votes
0answers
16 views

how to define objective function using linear programming for university timetabling problem?

I have been trying a lot define an objective function using linear programming for time scheduling problem. Our problem is allocation of classes to time and all the courses that student. I have a set ...
2
votes
0answers
30 views

Graph Neural Networks: Quesitons about different GCN Architectures

This might be moreof a question about nested function classes: For k class node classification in a graph with n nodes, and d feature vector. I want to compare Architecture I: the GCN model of Kipf/ ...
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
0answers
32 views

variational auto encoder loss goes down but does not reconstruct input. out of debugging ideas

My variational autoencoder seems to work for MNIST, but fails on slightly "harder" data. By "fails" I mean there are at least two apparent problems: Very poor reconstruction, for ...
2
votes
0answers
58 views

What place do Agent Communications Language have in Multi-Agent Systems nowadays?

I am currently working on implementing a Multi-Agent System for Smart Grids. There's a lot of literature for that and some things confuse me. I have read that there is FIPA, which aimed to create a ...
1
vote
0answers
32 views

What is the definition of pre-training?

I want to pre-train a model (combined by two popular modules A and B, and both are large blocks), then fine-tune it on downstream tasks. What if for the weight initialization for pre-training, module ...
1
vote
1answer
47 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
1answer
43 views

Is a team of ML scientists an “intelligent agent”?

I am writing about the role of machine learning scientists in developing a solution. Is there a term for the humans who do learning? Can we call a "team of machine learning scientists with their ...
2
votes
0answers
59 views

How can I use Monte Carlo Dropout in a pre-trained CNN model?

In Monte Carlo Dropout (MCD), I know that I should enable dropout during training and testing, then get multiple predictions for the same input $x$ by performing multiple forward passes with $x$, then,...
0
votes
0answers
18 views

Neural Network trains towards 1 despite target

So I'm trying to make my first neural network and have just finished my back propagation functions. I got the algebra from brilliant and thought I'd understood it, but my bug proves otherwise. The bug ...
2
votes
0answers
57 views

In few-shot classification, should I use my custom dataset as the validation dataset and mini-ImageNet as the training dataset?

I am new to few-shot learning, and I wanted to get a hands-on understanding of it, using Reptile algorithm, applied to my custom dataset. My custom dataset has 30 categories, with 5 images per ...
1
vote
0answers
63 views

VAE giving near zero output when latent space dimension is large

I'm training a VAE to reconstruct some input (channels picked up by some MIMO BS for context) and I ran an experiment on the training set to see how the performance improves with the latent space ...
2
votes
0answers
37 views

How and why do state-of-the-art models in medical segmentation differ from general segmentation models?

I am just getting into medical image segmentation and have been able to understand the state-of-the-art architectures, like Double UNet, UNet++, and Multiresunet. What I haven't understood yet: Why ...
4
votes
1answer
161 views

Is it really possible to create the “Perfect Cylinder” used in Universal Approximation Theorem for 1-hidden layer Neural Network?

There are proofs for the universal approximation theorem with just 1 hidden layer. The proof goes like this: Create a "bump" function using 2 neurons. Create (infinitely) many of these ...
0
votes
0answers
26 views

Which AI technique should I use for (key)point detection (in an image of a plantar pressure)?

I am relatively new to the field of AI. I have a problem that I would like to solve with AI, but I don't know which buzzwords I should use to search for solutions. I have a plantar pressure scan, like ...
0
votes
0answers
16 views

Is parameter sharing in AlBERT akin to repeated application of same function on input?

I read the AlBERT and saw that its architecture used "Parameter Sharing" among layers of the encoder. They mentioned that this was done to save model space, make fewer training parameters ...
0
votes
0answers
20 views

What's the best machine learning algorithm / neural network architecture to use for a task that maps between images and textual descriptions of them?

Title says it all really. I want to train a network to take images of diagrams and produce a standard textual definition of them. What ML architecture is best for this?
2
votes
0answers
29 views

In the Binary Flower Pollination Algorithm (using the sigmoid function), is it possible that no feature is selected?

I'm trying to use the Binary Flower Pollination Algorithm (BFPA) for feature selection. In the BFPA, the sigmoid function is used to compute a binary vector that represents whether a feature is ...
0
votes
0answers
62 views

Is my reward function non-Markovian?

I am working on an RL problem where the time when the agent obtains the reward for taking action $a$ in time step $t$ is stochastic. In fact, there is no immediate reward for taking action $a$ in time ...
0
votes
0answers
32 views

Multivariate time-series classification with many variables

I am attempting to use time-series classification algorithms for fraud detection applications. I have came across several works in the literature that propose novel techniques for multivariate time-...
3
votes
1answer
314 views

Why does regular Q-learning (and DQN) overestimate the Q values?

The motivation for the introduction of double DQN (and double Q-learning) is that the regular Q-learning (or DQN) can overestimate the Q value, but is there a brief explanation as to why it is ...
2
votes
1answer
53 views

How can I find words in a string that are related to a given word, then associate a sentiment to that found word?

I came up with an NLP-related problem where I have a list of words and a string. My goal is to find any word in the list of words that is related to the given string. Here is an example. Suppose a ...
2
votes
0answers
20 views

Can DQN outperform DoubleDQN?

I found a similar post about this issue, but unfortunately I did not find a proper answer. Are there any references where DQN is better than DoubleDQN, that is DoubleDQN does not improve DQN ?
2
votes
1answer
70 views

What algorithm would you advise me to use for my task?

I have an image and a mask. I want the image to be the same, but rotated, scaled and positioned like mask. What can I use?
0
votes
0answers
7 views

How to classify “composite” gestures from “primitive” gestures (with IMU data)

I'm exploring this idea: I record IMU data for "primitive" gestures (up-down, left-right, diagonal, circle...) I train a classifier to classify them (on my dataset, RandomForest achieves &...
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
54 views

How do you pass the image from one convolutional layer to another in a CNN?

I am currently trying to write a CNN from scratch, but I don't understand how to feed the information from a max-pooling layer to the next convolutional layer. Specifically, I don't know what to do ...
2
votes
0answers
27 views

Does there necessarily exist “dominated actions” in a MDP?

In a Markov Decision Process, is it possible that there exists no "dominated action"? I define a dominated action the following way: we say that $(s,a)$ is a dominated action, if $\forall \...
0
votes
0answers
18 views

Which loss function should I use to train DDGP with multiple q values, one for each of the output dimensions?

I'm trying to come up with a loss function for the case, in DDPG, where we have as many outputs from the critic as there are from the actor. So, there will be one Q value for each dimension in the ...
3
votes
1answer
131 views

How to use DQN when the action space can be different at different time steps?

I would like to employ DQN to solve a constrained MDP problem. The problem has constraints on action space. At different time steps till the end, the available actions are different. It has different ...
1
vote
0answers
46 views

Are actions deterministic during testing in continuous action space PPO?

In a continuous action space (for instance, in PPO, TRPO, REINFORCE, etc.), during training, an action is sampled from the random distribution with $\mu$ and $\sigma$. This results in an inherent ...
3
votes
0answers
80 views

Why is the margin attained with $\Phi=\left[2 x, 2 x^{2}\right]^{T}$ greater than the margin attained with $\Phi=\left[x, x^{2}\right]^{T}$?

I am trying to understand the solution to part 4 of problem 3 from the midterm exam 6.867 Machine learning: Mid-term exam (October 15, 2003). For reproducibility, here is problem 3. We consider here ...
0
votes
0answers
23 views

Is there a reference that describes Recurrent Neural Networks for NLP tasks?

I would like some references of works that try to understand the functioning of any kind of RNN in natural language processing tasks. They can be any work that tries to explain the functioning of the ...
0
votes
0answers
18 views

Recommended vehicle trajectory prediction algorithms (based only on lat/lon data)?

Could you recommend me the most suitable algorithms for vehicle trajectory prediction? Although I'm studying kalman filter approaches and they are the most used, are there other common (NN, SVM, RF, ...
2
votes
0answers
48 views

How does bootstrapping work with the offline $\lambda$-return algorithm?

In Barton and Sutton's book, Reinforcement Learning: An Introduction (2nd edition), an expression, on page 289 (equation 12.2), introduced the form of the $\lambda$-return defined as follows $$G_t^{\...
1
vote
2answers
126 views

If the training data are linearly separable, which of the following $L(w)$ has less optimum answer for $w$, when $y = w^Tx$?

I'm studying machine learning and I came into a challenging question. The answer is 2. But based on my ML notes, all of them are true. Where are the wrong points?
4
votes
1answer
181 views

How can a probability density value be used for the likelihood calculation?

Consider our parametric model $p_\theta$ for an underlying probabilistic distribution $p_{data}$. Now, the likelihood of an observation $x$ is generally defined as $L(\theta|x) = p_{\theta}(x)$. The ...
0
votes
0answers
31 views

Which is the best algorithm to predict the trajectory of a vehicle using lat/lon data?

I'm using Kalman Filter approaches and I've just implemented the extended Kalman filter (EKF) with my object 2D trajectory. However, I have a mess of alternative approaches that may fit better like ...
1
vote
1answer
903 views

How to understand 'losses' in Spacy's custom NER training engine?

From the tid-bits, I understand of neural networks (NN), the Loss function is the difference between predicted output and expected output of the NN. I am following this tutorial, the losses are ...
2
votes
0answers
69 views

$\nabla \log \pi$ with respect to some parameters constantly being zero

I am new to reinforcement learning. May I ask a simple (and maybe a bit silly) question here? I am trying to use the "one-step actor-critic" method to train a robot on a gridworld. Let's ...
0
votes
0answers
23 views

During Backpropagation in LSTM, why is the previous output $h_{t-1}$ considered constant w.r.t any $W$ while computing derivative?

I've just started learning LSTM, and some points in the process of calculating the gradients are getting me confused. Say, for example, we want to compute $\frac{\partial}{\partial W_i}L$, where $L$ ...
2
votes
1answer
30 views

How does DDPG algorithm know about my action mapping function?

I am using DDPG to solve a RL problem. The action space is given by the Cartesian product $[0,20]^4\times[0,6]^4$. The actor is implemented as a deep neural network ...

15 30 50 per page
1
28 29
30
31 32
185