Questions tagged [research]
The research tag has no usage guidance.
56
questions
0
votes
1
answer
13
views
Data Mining of unresearched data for a master's degree final project
So, I have to start thinking about the topic of my final project in a data science master's degree (business oriented, although I can choose any unrelated field) and one of the requirements is to ...
2
votes
1
answer
296
views
How do researchers actually code novel architectures and layers?
Disclaimer: I am almost a complete novice when it comes to tensorflow, keras, coding in general, and neural networks/data science.
While reading papers on novel architectures for neural nets, I see ...
1
vote
0
answers
22
views
Zero-shot learning for tabular data?
Can anyone point me to methods for zero-shot learning on tabular data? There is some very cool work being done for zero-shot learning on images and text, but I'm struggling to find work being done to ...
1
vote
0
answers
14
views
Machine learning frameworks for tree-based models
Background: Its well known that Pytorch and TensorFlow are currently the most used frameworks for Deep Learning (DL) research. As far as I know, most researchers (applied or theoretical) that ...
0
votes
0
answers
15
views
Topic / concept learning difficulty prediction
I was exploring the field of learning analytics. A bunch of research papers are focused on predicting course scores or grades. But, I was searching for predicting which concepts/topics students find ...
0
votes
0
answers
11
views
Model does not learn after ternarization of weights contrary to the paper mentioned below
I’m implementing the ‘Ternary Weights Network’ paper by Fengfu Li and Bo Zhang ( archive link - https://arxiv.org/abs/1605.04711).
I’m training a simple Covnet with linear layers on the MNIST dataset. ...
1
vote
0
answers
15
views
Dataset for IoT activities [closed]
First of all, I am not sure whether this is the correct Stackexchange site for this question. If not, please let me know :)
My question: I am looking for a dataset pertaining to IoT activities. ...
1
vote
2
answers
46
views
For a student who is a beginner in quantitative research and statistics, which is the better statistical tool to start: R or IBM SPSS? Why? [closed]
Currently, I am writing my research design. However, I am still indecisive on what statistical tool should I use for the data analysis. I tried looking up on the internet and there are disparate ...
0
votes
0
answers
44
views
What does the term "seed lexicon" means?
I am reading a research paper (NLP) and found the phrase "seed lexicon".
Could someone please explain it in detail?
Edit :
A sample paper
Leveraging Affective Bidirectional Transformers for ...
1
vote
0
answers
22
views
Should I reshuffle the training set when benchmarking neural networks?
I'm trying to set up a fair benchmarking between various RNN models, where each of them is trained until convergence with a fixed random seed. Because the task is very costly, I am only able to run ...
0
votes
0
answers
7
views
Can we consider Meta-features of a datasets as its embeddings?
While reading some works on meta-learning. I had this doubt.
Can we consider meta-features of a dataset as it's embedding ?
Given the meta-feature is a lower dimensional representation which also try ...
1
vote
1
answer
27
views
Developing a deep learning hybrid architecture for a particular problem is a highly complicated task [closed]
I am currently conducting research on application of deep learning (sensor signal recognition). I spent about a year and a half sifting through the literature and discovered some research patterns. To ...
0
votes
0
answers
48
views
Interactive plot of topics over time
I am working on an NLP program to extract and analyze topics of research papers based only abstracts.
I would like to have a plot like this one:
But when I click on a line I would like to have a new ...
1
vote
0
answers
30
views
[Guidance Needed]Research in data science [closed]
IMAGINE
You're a research intern and you're an undergraduate student. Have
some experience in data science and now new to research.
Your task is to conduct research on vision transformers. Oh and by
...
0
votes
2
answers
21
views
Spectral Networks and Deep Locally Connected Networks on Graphs
I’m reading the paper Spectral Networks and Deep Locally Connected Networks on Graphs and I’m having a hard time understanding the notation shown in the picture below (the scribbles are mine):
...
3
votes
1
answer
67
views
How to determine the abnormality of a specific variable by taking into account all the other variables in the data?
I have an issue of machine learning/anomaly detection. Indeed, I have a variable Y and several other variables X. The purpose is to quantify the degree of abnormality of the data on Y but I have to ...
1
vote
0
answers
40
views
Custom Loss Function Equation
I am trying to reproduce a research paper, where it is a classification problem, and they have introduced a custom loss function that I am unable to understand.
Now I think I have to implement the ...
1
vote
1
answer
19
views
How to conclude the generality of any classification methods?
Suppose a classification task A, and there exist a lot of methods $M_1, M_2, M_3$.
The task $A$ is measured by a consistent measure.
For instance, the task A can be a binary classification. In this ...
0
votes
2
answers
54
views
Actual problems in Data Science/Machine Learning connected with music [closed]
I'm on my $4^{th}$ year now and searching for a theme for my diploma in mathematics & computer science specialization.
Is there are interesting problems or fields for researches that i can explore?...
0
votes
1
answer
106
views
How do we know a neural network test accuracy is good enough when results vary with different runs?
In every paper I read about prediction models, the training accuracy and the test accuracy (sometimes also the validation accuracy) is stated as a discrete number. However, in experience, depending on ...
0
votes
0
answers
77
views
What is the time complexity of learning/testing phase neural network?
What is the time complexity of feed-forward neural networks? I didn't find a book or a reliable source that's talks about this. This link provides one version by breaking the structure of a simple ...
0
votes
1
answer
58
views
Will the job of Data Science is going to be at risk? [closed]
Data Science is the sexiest job of 21st Century according to the different sources with a high payment salary . But it seems that there will be over production of this profession . According to U.S. ...
1
vote
2
answers
93
views
In "Attention Is All You Need", why are the FFNs in (2) the same as two convolutions with kernel size 1?
In addition, why do we need a FFN in each layer when we already have attention?
Here's a screenshot of the relevant section from Vaswani et al. (2017):
0
votes
1
answer
291
views
Is there a reference data set for ridge regression?
In order to test an algorithm, I am looking for a reference data set for ridge regression in research papers. Kind of like the equivalent of MNIST but for regression.
3
votes
1
answer
225
views
Need an advice on research topic [closed]
I am about to choose ML research topic for my master thesis, but i am at a dead end. The problem is, that while reading research papers, i find solutions, but not an open problems.
For now, a came up ...
0
votes
1
answer
23
views
Previous work Replication and Research ethics Ask Question
I am very much concerned about biding by research ethics in my work, especially issues to do with plagiarism. I come across a recent research paper in my field of study that applies state-of-the-art ...
1
vote
0
answers
52
views
Where can I find datasets suitable for an undergraduate research project? [closed]
I have tried Kaggle but couldn’t find anything suitable. Basically I want to do a machine learning or deep learning project. Ideally it would have something to do with computer forensics or security. ...
1
vote
0
answers
129
views
Transitioning from Math PhD to ML research [closed]
I am currently a Math PhD about to defend in January. I work in a field in functional analysis that uses a lot of measure theory (but no stats).
I have been considering transitioning careers since I ...
1
vote
1
answer
113
views
T-DBSCAN - Implementing STOP logic
I am attempting to implement the T-DBSCAN algorithm described in T-DBSCAN: A Spatiotemporal Density Clustering for GPS Trajectory Segmentation. I have been able to implement most of the logic between ...
4
votes
5
answers
378
views
Classification training using probabilites and not raw classes (factors)
I have a problem where instead of having classes, i.e. a vector of 0s and 1s, I have the probability of an observation belonging to a class.
A vector with 0.1, 0.95, 0.2, 0.3, etc.
The obvious ...
1
vote
2
answers
100
views
Testable hypotheses construction; minimum predictive strength vs. significance
Is this null hypothesis TESTABLE?
Research Question: "Can a predictive model utilizing logistic regression be built which predicts at least one customer will churn in 90 days, and this individual ...
1
vote
1
answer
328
views
Site for implementing a research papers without code
Before a couple of months, I found a web page for implementing papers which are published without code. Someone posts a paper on it and then community competes to implement that paper.
But I don't ...
1
vote
1
answer
215
views
Mapping between original feature space and an interpretable feature space
I'm reading the following really interesting paper
https://arxiv.org/pdf/1602.04938.pdf on local interpretable model explanations
on page 3 however particularly section 3.3 Sampling for Local ...
3
votes
1
answer
55
views
How can there be more true positive than positive?
Currently reading Learning from Little: Comparison of Classifiers Given Little Training
In 3 Experiment Results, the following graph is shared:
The experiment is described as follow
We begin by ...
0
votes
1
answer
20
views
Will data science develop into a separate academic field? [closed]
Right now data science is often regarded as an interdisciplinary subfield of statistics and computer science. What would it take for data science to develop into a separate academic field (with its ...
1
vote
0
answers
371
views
Performance of UNet on low resolution images
I read the U-Net paper yesterday and it talked mostly about how it uses a small dataset (<100) of high-resolution images and performs efficiently.
I was wondering how it might perform on larger ...
3
votes
2
answers
111
views
What is the loss function defined by Mnih and Hinton in their paper “Learning to Label Aerial Images from Noisy Data”?
In section 3.3 of the paper, they state that they use the cross entropy.
Then they define the probability for a label to be a false positive as $\theta_0$ and a false negative as $\theta_1$.
They use ...
1
vote
1
answer
155
views
Adversarial attacks on non image data
Reading the literature around deep learning adversarial attacks it appears to be wholly concentrated on attacks of image classification models. Are there papers that describe attacks on non image data ...
3
votes
2
answers
294
views
How to measure Entity Ambiguity?
When using/building a system for Entity Linking, is there a well-known measure for "ambiguity degree" of an entity?
Some approach to compare named entities regarding how difficult to disambiguate?
1
vote
1
answer
103
views
Does it make sense to parallelize machine learning algorithms as part of PhD research? [closed]
I'm developing machine learning algorithms to aid in the diagnosis and prognosis of various cancers for my PhD. My lab is an Nvidia teaching center (CUDA).
My supervisor thinks that I need to also ...
1
vote
0
answers
24
views
Possibility of self-growing neural nets
What is the state of the art for DNNs to infer that they need more neurons than in the initial setup? Can they be acquired dynamically from the underlying "resource substrate"?
1
vote
1
answer
208
views
Is machine learning successful in solving combinatorial optimisation problems in NP-hard? Discuss problem of scheduling using machine learning [closed]
Chess is Exp-complete. I assume Alpha GO is also Exp complete. Correct me if I am wrong. Now deep reinforcement learning has been successful in tackling this problem. What about other more practical ...
1
vote
0
answers
269
views
Measures for choosing the best Decision Tree split?
I'm searching for a paper or book that list several possible measures for deciding which variable to split a Decision Tree at.
The basic ones are well known and very well documented in several ...
4
votes
4
answers
347
views
What kind of regression model should I do?
my research question is the examine the effect of "receiving attention" from other members in an online community on "sustained participation" on the website.
I decided to measure "sustained ...
2
votes
1
answer
343
views
Deep learning facial recognition research project
I'm a second year pure maths, applied maths and computer science student. I have taken up a research course and was given the topic to focus on facial recognition using deep learning.
I have done a ...
-2
votes
2
answers
3k
views
Master thesis topics [closed]
I am looking for a thesis to complete my master, I am interested in Predictive Analytics in marketing, HR, management or financial subject, using Data Mining Application.
I have found a very ...
1
vote
0
answers
944
views
Multi Model data set Visualization Python
I have a data-set with two variable frequency values as given below
...
3
votes
1
answer
759
views
Determining completeness of dataset
I'm hoping you have some research or experience with determining the completeness of a data set. I'm trying to use a twitter dataset I scraped myself and want to have an indication on the completeness....
1
vote
1
answer
2k
views
The implementation of overlapping clustering (NEO-K-Means)
I am researching on overlapping clustering (Clusters are non-disjoint).I found that Neo-K-Means is probably the state-of-the-art now.But, when I tried implementing the algorithm with the multi-label ...
3
votes
1
answer
1k
views
Identify given patterns in unstructured data like text files
I wasn't sure if I had to ask it here or in Stackoverflow, but since I am also seeking research papers/algorithms and not only code, I decided to do it here.
When I have a text, I can manually write ...