Skip to main content

Questions tagged [reference-request]

"References" is our generic tag for questions seeking information about books, papers, presentations, videos of lectures, on-line tutorials, etc., regarding any subject matter that is on-topic for Data Science.

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

Best practises for creating datasets for the purpose of finetuning LLMs

I am working on a problem for which no datasets exist. I have obtained several examples from this domain, and so far have been using them in Large Language Model (LLM) prompts(few shot learning) but I ...
Karl 17302's user avatar
0 votes
0 answers
57 views

Preparation for data scientist interviews/job for final year PhD student in ML theory

I would like to check/ask if there is anything particular that I need to prepare for data scientist interviews. I am quite unsure/lost about the requirements since I am coming from academia (see my ...
Resu's user avatar
  • 101
1 vote
1 answer
497 views

Why is 0.7, in general, the default value of temperature for LLMs?

I have recently read through a lot of documentation and articles about Large Language Models (LLMs), and I have come to the conclusion that 0.7 is, most of the time, the default value for the ...
jmpion's user avatar
  • 11
0 votes
1 answer
43 views

Suggestions to learn the Machine Learning models in greater depth?

I've been learning machine learning for the past few weeks from books and online courses. The books I've been reading, and currently still reading is "Hands-On Machine Learning with Scikit-Learn ...
Justin Jonany's user avatar
0 votes
0 answers
19 views

Harford 2023 model: explicit reference

I'm citing in a paper the Wizard-Vicuna Uncensored 30B model of Hartford (2023). But I don't have an exact bib reference other than various web links for that model. Could anyone help?
cel's user avatar
  • 1
0 votes
0 answers
36 views

Does clustering belong to the domain of data mining or to the domain of machine learning?

Question 1. Does clustering belong to the domain of data mining or to the domain of machine learning? Or to both domains? Question 2. Depending on the answer to Question 1, could you please suggest a ...
Ommo's user avatar
  • 103
1 vote
0 answers
19 views

Are "textbook backpropagation" still relevant?

The above backpropagation algorithm is taken from Shalev Shwartz and Ben-David's textbook: Understanding Machine Learning. This algorithm is described in the same way as the one in Mostafa's textbook, ...
Fraïssé's user avatar
  • 119
0 votes
0 answers
167 views

Store and retrieve multiple documents in free vector stores based on critria

I am new to vector stores, and so far experimented with storing 1 file in Faiss and Pinecone. I am looking for tutorials that teach me how to save multiple files in free versions of any vector store, ...
IwillLearn's user avatar
0 votes
1 answer
39 views

How to use API Documentation of dataset

Some websites provide a link to a dataset (in Excel sheets format) which allows the dataset to be downloaded. But some others additionally provide API documentation, like this site. Can you please ...
IwillLearn's user avatar
0 votes
1 answer
88 views

Is it ok to normalize data using minmaxscalar on dependent variable?

I'm trying to make a sales prediction using the column X = item_amount and y = item_price_total, I'm confused whether it's okay to normalize data on the dependent variable using minmaxscalar? With the ...
Fatur's user avatar
  • 1
0 votes
0 answers
25 views

What (ML) algorithms take an image as input and optimal action as output?

I have a given 2d image describing a top down view of a grid (think e.g. a labirynth.) I want an algorithm to take it as an input and return a single action to be performed in the setting of this grid....
user150717's user avatar
0 votes
0 answers
16 views

How can a pullback dissimilarity on a nasty space be interpolated/approximated?

I have a map $\gamma : X \rightarrow Y$ that is expensive to compute. $X$ is a nasty, very non-Euclidean, not even manifold-like, space of variable-length and "structurally inhomogeneous" ...
Steve Huntsman's user avatar
4 votes
1 answer
51 views

Resources for Promotion/Demotion Strategies for ML Item Recommendation Systems?

We are looking to design a system where specific items or categories of items can be boosted/promoted up or relegated/demoted down the recommendation order. What are the common strategies or standards ...
JPTheEngineer's user avatar
0 votes
3 answers
1k views

How to remove outliers properly?

I was wondering what is the best practice for removing outliers from data. Plotting a boxplot for each feature (column of the dataset) and removing data that fall outside the whiskers seems like a ...
Erik M's user avatar
  • 83
1 vote
1 answer
65 views

What are the possible applications of a Data Scientist in the design fase of an Aerospace Or Railway Engineering industry? [closed]

I have been trying to understand this for a long time, but this information proves to be incredibly elusive online. What are possible jobs that a pure Data Scientist, without much background knowledge,...
temporario1001's user avatar
0 votes
1 answer
652 views

Word Embeddings fastText in 50 dimension

Is there a fastText embedding in 50 dimensions? I'm aware of GloVe embedding is dimensions (50, 100, 200, 300) dimensions. I am trying to sentiment analysis with a very small dataset. If there is ...
cris2019's user avatar
2 votes
1 answer
198 views

Rate of convergence - comparison of supervised ML methods

I am working on a project with sparse labelled datasets, and am looking for references regarding the rate of convergence of different supervised ML techniques with respect to dataset size. I know that ...
Avatrin's user avatar
  • 131
3 votes
1 answer
63 views

References/tutorials about data mining and machine learning

I am learning data analytics and I wonder if there are some good references and tutorials about machine learning, data analytics and data mining. What I'm searching for is an understandable reference/...
plpm's user avatar
  • 155
1 vote
0 answers
43 views

What are some good resources for setting up and debugging neural networks?

I am aware of Troubleshooting Deep Neural Networks by Josh Tobin and A Recipe for Training Neural Networks by Andrej Karpathy, but I am interested in other resources that can give me some guidelines ...
mhdadk's user avatar
  • 131
8 votes
1 answer
374 views

Who invented the concept of over-fitting?

I list the references that I found so far. Shortly, the first appearance of the term was in 1670, first appearance in in close meaning was in 1827, first appearance in a biological paper was in 1923 ...
DaL's user avatar
  • 2,633
1 vote
0 answers
125 views

Machine learning for circular sequences

My data are sequences of real numbers $a_0,a_1,...,a_{n-1}$. The length of a sequence is fixed and equals $n$. Each sequence is mapped to a real number $y$ and I want to predict $y$ given the sequence....
Vladislav Gladkikh's user avatar
2 votes
0 answers
135 views

What is the difference between ICR and OCR?

I've just found the term "Intelligent Character Recognition" (ICR) on Wikipedia and other pages. According to Wikipedia: In computer science, intelligent character recognition (ICR) is an ...
Martin Thoma's user avatar
  • 18.9k
0 votes
1 answer
82 views

Where to upload large (0.5Gb) weights anonymously?

I need to upload a number of checkpoints for ConvNets (weights + optimizers, all dicts of pytorch tensors), each about 0.5Gb anonymously. I don't want to use Google Drive. I trained models on the ...
Alex's user avatar
  • 767
3 votes
1 answer
120 views

Outlier/Anomaly Detection History

I have been reading about different methods of anomaly detection, their structure and the way they work. Recently I have been trying to find some scholar articles, writings or books where I can learn ...
E199504's user avatar
  • 605
2 votes
1 answer
20k views

What is "lag" in time series forecasting?

I'm studying machine learning (e.i. time series analysis). I encountered an Azure tutorial, Retail Forecasting. https://gallery.azure.ai/Experiment/Retail-Forecasting-Step-2-of-6-train-time-series-...
hgshin's user avatar
  • 21
2 votes
0 answers
33 views

What could be proper terms for a research direction in natural language processing to measure meaningfulness?

For some time, I did assessments to design metrics on how to recognize well-written and meaningful software requirements. Then I decided to work with Stack Overflow question posts because they are a ...
Open Food Broker's user avatar
2 votes
1 answer
2k views

Tutorial for restricted Boltzmann machine using PyTorch or Tensorflow?

I am trying to find a tutorial on training Restricted Boltzmann machines on some dataset (e.g. MNIST), using either PyTorch or Tensorflow. The few I found are outdated. Can you recommend any?
a06e's user avatar
  • 129
10 votes
4 answers
2k views

Math PhD (Nonlinear Programming) switching to Data Science?

I am a math Ph.D. student who is interested in going to the industry as a Data Scientist after graduation. I will briefly give some background on my education before posing my question, so that it is ...
John D's user avatar
  • 123
1 vote
1 answer
679 views

How CNN applies backpropagation to update its weights and biases?

I understand that the 3 main layers for CNN are convolutional layer, ReLU layer and pooling layer. However, I do not understand how CNN updates its weights and biases using backpropagation. I ...
Idonknow's user avatar
  • 101
1 vote
1 answer
51 views

Book about distances for data science (can't remember the name)

I saw a book somewhere that listed a big amount of mathematical distance functions (the usual euclidean norms, the discrete distance, the hamming distance, etc) used for data science. The name of the ...
Guillermo Mosse's user avatar
1 vote
1 answer
64 views

How has data generation evolved over the years (and centuries)?

I would like to know how data generation has evolved through the years. My end goal would be to generate a logarithmic line plot showing the ridiculous increase in data generation. Please, does ...
Guillermo Mosse's user avatar
4 votes
2 answers
1k views

Given a machine learning algorithm, what is the minimum size of the training set for it?

I understand that the more data we have, the more reliable is our model trained on that data. I also understand that the more parameters a machine learning model has, the more training data it ...
Vladislav Gladkikh's user avatar
1 vote
0 answers
21 views

Correlation between (average daily) impressions and user response ratio in social media

I'm doing a preliminary study on data from a (niche) social media platform. Studying the correlations between impressions of an object (aka views), interactions (aka likes, comments, ...) and their ...
dcolazin's user avatar
  • 161
4 votes
1 answer
2k views

What is the best practice to test a ETL pipeline?

In traditional software development practice, before going into production, a piece of code should go through various stages of testing (unit test, integration test, user acceptance test) to secure ...
Costa's user avatar
  • 41
0 votes
1 answer
94 views

Protein interaction prediction- how to input this data structure

I know the basics of machine learning and have quite an experience with time series data or data fed in a tabular format. But in the picture, the data is arranged as a graph. Is there a way to input ...
Srishti M's user avatar
  • 471
1 vote
0 answers
205 views

Recognition of objects in almost plain background

I want to recognize climbing holds in a climbing wall. I thought about implementing my own heuristic algorithm for background detection because it's almost plain, but I was wondering if this kind of ...
Quimey's user avatar
  • 111
2 votes
1 answer
536 views

Do 3D bar charts have advantages over 2D bar charts?

I vaguely remember that there was a study / blog post which made a strong point against 3D bar charts. Do you have a source at hand which compares the two - 2D bar charts and 3D bar charts?
Martin Thoma's user avatar
  • 18.9k
0 votes
1 answer
78 views

algorithm to auto-download articles from the internet

I have an issued in my homeworks and I thinked if there is an rxisted algorithm or if can i create new one that takes key words like "germany" and "polution" and parses in google scholar. It parses ...
Linda's user avatar
  • 9
4 votes
2 answers
170 views

Why Gradient methods work in finding the parameters in Neural Networks?

After reading quite a lot of papers (20-30 or so), I feel that I am quite not understanding things. Let us focus on the supervised learnings (for example). Given a set of data $\mathcal{D}_{train}=\{...
induction601's user avatar
1 vote
0 answers
22 views

Learning Attention Based Models [books]

Today I read an interesting post to drop RNNs for sequential models. However, the post, unfortunately, didn't go into much detail on how one would study the attention based models and start ...
GRS's user avatar
  • 183
8 votes
5 answers
2k views

Mastering NLP: Reading List

I've searched the web and there are hundreds of recommendations on what to read. The time moves on and new better quality techniques are published, so I would like to know what is relevant in 2018? ...
GRS's user avatar
  • 183
0 votes
3 answers
1k views

Forecast vs Prediction: What is the difference?

I use the two terms as follows: A prediction model gets features (which can be a time series) as input and gives a fixed-length output (might be multiple values, but "atomic" in some sense) Examples:...
Martin Thoma's user avatar
  • 18.9k
4 votes
1 answer
158 views

Common Techniques to Generate from a Regression Neural Network Model

I am used to train neural networks that are designed for generation, such as GANs or VAEs. I am wondering what are the common techniques to generate data that would minimize the target/energy learned ...
Toool's user avatar
  • 141
1 vote
1 answer
33 views

Voting patterns similarities

I'm interested in any research materials on voting patterns. I have a data set of how PMs (members of parliament) voted in my country during last couple of years. Each PM has 3 buttons: Yes, No, ...
Igor's user avatar
  • 139
2 votes
2 answers
730 views

Help me choose a Data Science book in Python [closed]

I've been a Data Scientist for a few years now, but I've only recently started to do most of my work in Python (boy, do I miss ggplot2! But ...
DeltaIV's user avatar
  • 399
7 votes
3 answers
6k views

Is there any proven disadvantage of transfer learning for CNNs?

Suppose I know that I want to use a ResNet-101 architecture for my specific problem. There are ReseNet-101 models trained on ImageNet. Is there any disadvantage of using those pre-trained models and ...
Martin Thoma's user avatar
  • 18.9k
1 vote
2 answers
209 views

What is the relationship between AI and data science?

I think they share a lot (e.g. machine learning is a subset of both, right?), but maybe both have elements the other doesn't have? Could you name some in that case? Or is one a subset of the other? ...
1 vote
0 answers
149 views

ElasticSearch for data scientists [closed]

This is to seek career advice for a data scientist. What pertains within the role of data scientist and what does not regarding ElasticSearch. Does backend development for ElasticSearch using ...
StatguyUser's user avatar
16 votes
5 answers
4k views

Beginner math books for Machine Learning

I'm a Computer Science engineer with no background in statistics or advanced math. I'm studying the book Python Machine Learning by Raschka and Mirjalili, but when I tried to understand the math of ...
1 vote
0 answers
28 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"?
Open Food Broker's user avatar