Questions tagged [supervised-learning]

Supervised learning is the machine learning task of inferring a function from labeled training data. The training data consist of a set of training examples. In supervised learning, each example is a pair consisting of an input object (typically a vector) and a desired output value (also called the supervisory signal). A supervised learning algorithm analyzes the training data and produces an inferred function, which can be used for mapping new examples.

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

When testing a trained model, what do you use for x_test and y_test when you started with a separate test set without a target variable? [closed]

In this html file, I'm trying to get a CSV file by doing the model testing on a test dataset - w/o a target variable - that I was given at the beginning of a project. I'd greatly appreciate it if ...
2 votes
1 answer
81 views

How to *formalize mathematically* that a binary classifier has no predictive performance?

The objective of supervised learning is to induce a function $f_\theta$, where $f_\theta$ is from a family of functions $f_\theta \in F$, from a training set $D^{tr}=\{(x_0^{tr},y_0^{tr})\ldots, (x_n^...
1 vote
1 answer
22 views

Does Discriminator in GAN Train only on Real Data or it also Trains on Fake Generated Data

I have been studying GANs and I got confused in the training phase from the discriminator. Which I think only trains on Real data, not on the generated data which then helps in distinguishing or ...
1 vote
0 answers
9 views

How to interpret the relationship between batch size and bootstrap count in a specific paper?

In the paper "Active Learning for Natural Language Parsing and Information Extraction", the author mentioned: In tests on this data, test examples were chosen independently for 10 trials ...
  • 79
1 vote
1 answer
10 views

why we use same learning rate in the whole process of the gradient descent?

In theory, we know while we are descending to the point where the error is zero, we give big steps that are learning rate will be big. And when we are near to the error equal to zero we start giving ...
  • 657
3 votes
0 answers
32 views

loss function for supervised anomaly detection in time series [closed]

I have a supervised anomaly detection problem in a time series data, which the dataset has three columns: datetime value(a float number) label(1 for anomaly, 0 for normal) It's common that the ...
3 votes
0 answers
21 views

Are there examples of ML or stats approaches that are valid for IID data, but not exchangeable data?

Lots of supervised learning theory is motivated using the IID assumption. Do most of these methods apply equally well if data is only exchangeable, and not IID? Can you provide an example where this ...
0 votes
0 answers
12 views

ML classifier comparison questions

I got some review comments as below from the conference panel regarding my results They are comparing unsupervised learning (KNN, Linear Regression) to supervised learning (CNN, RF). How are they ...
0 votes
0 answers
24 views

Neural network architecture for supervised sequential learning

The objective is to model data with the following structure (training data): feature_1 feature_2 feature_3 feature_4 Output 0.15 0.85 0.46 0.99 0 0.88 0.34 0.17 0.09 1 0.24 0.71 0.50 0.81 0 0.35 ...
  • 278
0 votes
0 answers
23 views

Is it appropriate to use cross validation if I'm not hypertuning my parameters or testing different models?

I am making a machine learning model with supervised classification. I want to input my data, cross validate my model and then test it on a test set. Finally, I will use this to transform/make ...
1 vote
0 answers
19 views

Is there an implicit independence assumption in Bayesian inference between X and parameters?

I often see things like $$ p(w|X,y) \propto p(y|X,w) p(w)$$ where $w\in\mathbb R^p$ denotes some parameters, $y\in \mathbb R^n$ denotes some observed outcome values, and $X\in \mathbb R^{n\times d}$ ...
0 votes
0 answers
68 views

Why is there a difference between training and validation accuracy when both of them are pointing to the same subset?

I was training a model and I accidentally pointed the training and testing set to the same dataset. I was surprised by the fact the validation and training accuracy are not the same. What could be the ...
1 vote
0 answers
35 views

Unsupervised learning (clustering) before supervised learning [closed]

Is it a common practice to do clustering before supervised learning to eliminate "noisy data"? Obviously, depending on the type of task. It seems like it makes sense in my case and my neural ...
  • 11
0 votes
0 answers
20 views

What is the mathematical term for a real world categorical function that yields several categories for the same inputs?

Background and Color Contextually, this is pertaining to machine learning and natural language processing. Specifically, it has to do with the labeling of real world data for partitioning by a machine ...
  • 306
0 votes
0 answers
6 views

comparisons of true-labels and model predictions: a spectrogram or a heatmap?

In a classification task, confusion matrix shows the number of example say, a model A predicts correctly, and those misclassfied. But is doesn't show exactly which particular instances of class ...
  • 1
2 votes
1 answer
15 views

can we use odds ratio for the risk estimation in support vector machine regression?

I want to compare the logistic regression model and support vector machine regression. odds ratio is used in logistic regression. can we use odds ratio in support vector machine regression.???
1 vote
0 answers
27 views

Why separating the data in training and test sets is not feasible in unsupervised learning problem?

Based on my understanding: Unsupervised learning problems are modeling data with no labels. Hence, we try to cluster a given data into clusters. Supervised learning problems are modeling data with ...
  • 1,170
1 vote
0 answers
34 views

KNN(k-nearest neighbor) algorithm as supervised and as unsupervised algorithm. What are the main differences? How can it be both?

On internet and in articles KNN ist mostly described as supervised algorithm. But recently I have find also few articles where it is mentioned as unsupervised algorithm.I cannot find articles that are ...
1 vote
0 answers
24 views

Interpreting learning curves

There is really few examples online regarding interpreting learning curves and they are all of different type.It is quite confusing to me honestly.May I just ask: How should we interpret them?What ...
1 vote
0 answers
85 views

Chicken and egg problem in machine learning [closed]

Recently, I went through an ICLR paper SELF-LABELLING VIA SIMULTANEOUS CLUSTERING AND REPRESENTATION LEARNING. In the paper, authors discussed simultaneously labeling the images and training a network ...
0 votes
1 answer
30 views

"SMOTE makes the assumption that the instance between a positive class instance and its nearest neighbors is also positive"

I am trying to get my head around this assertion by Liu, Y. et al (2011 pp. 7) about SMOTE oversampling technique that: because SMOTE makes the assumption that the instance between a positive class ...
  • 231
0 votes
0 answers
13 views

Can a basis expansion guarantee no worse performance than original features?

Consider the typical learning problem where given inputs $x_i \in \mathbb{R}^p$ and targets $y_i \in \mathbb{R}$ for $i = 1, \dots, n$ we would like to learn some function $f$ such that $L(f(x_i), y_i)...
  • 456
0 votes
0 answers
28 views

How do I evaluate if my data represent the target variable before training a machine learning algorithm?

I have a dataset of points cloud where each point in the point cloud has a variable. I am trying to relate the local geometry features to that point variable by using FPFH, This means I am generating ...
0 votes
1 answer
43 views

In which category falls a mix of unsupervised and supvervised learning?

Here is the context of my problem: I want to classify between to classes. However, I have at disposal only non labeled data to do the training (the test set possess all labels for evaluation purposes)....
  • 9
3 votes
0 answers
56 views

Looking for the Holy Grail of nonparametric regression

Unfortunately, to state precisely the question, I need some formal preliminaries. Let $d \in \mathbb{N}$. For each $d^* \in \{1,\dots,d\}$, define $\mathcal{M}_{d^*}$ be the set of probability ...
  • 173
2 votes
1 answer
46 views

Terminology of "Regression forest", "Random forest", "Decision tree" and "Regresion tree"

I am confused about the terminology of "regression forest", "random forest regression", "random forest", "decision tree" and "regression tree". As far ...
  • 109
1 vote
1 answer
28 views

I have set of features to relate to two different values. When I made a regressor for only one it worked well but if i use two it does not?

I have a set of 33x1 features (x) and they can be related to different two values in (y) and I have 1203985 observations. Using np.shape() you can see the dimensions of x and y. x= (1203985, 33) y=(...
1 vote
1 answer
16 views

Problem formulation classification task

I would like to know if it is correct for a classification task in a supervised learning to say the model we are looking for is a function from RxR to a discrete space $$ f:\mathbb{R}\times\mathbb{R} \...
1 vote
1 answer
50 views

What part of a dataset do I apply a traditional, statistical analysis to linear regression?

Note: I've edited my question as recommended below by @EdM. Suppose I have a supervised learning problem on a sizeable tidy dataset with real values—-e.g., the dataset has 100,000 rows or observations....
0 votes
1 answer
181 views

Can all neural network layers be used as either a supervised or an unsupervised model?

I am trying to understand neural networks and by reading different articles I always find conflicting information. I wanted to understand which neural networks can be used as supervised/unsupervised. ...
  • 116
3 votes
3 answers
156 views

Challenge an ICML Paper: For a given set of probability predictions and a log loss value, is the set of true labels giving such a loss unique?

Aggarwal's 2021 ICML paper "Label Inference Attacks from Log-loss Scores", seems to argue that the answer to the question in the title is "YES". The paper claims that, given ...
  • 35.4k
1 vote
0 answers
33 views

What is the difference between these two types of training?

Suppose that I want to detect if a picture contains a particular logo, for instance the following one. Since template matching would be slow and fail those scaled or resized ones, I decided to train ...
  • 5,436
0 votes
0 answers
12 views

Unconventional pretext task in computer vision - can I somehow justify it?

I was working on a industrial object detection neural network project. Since we had multiple images of the same object in different (but fixed) positions and light conditions, our dataset was very ...
0 votes
0 answers
19 views

When is the existence and/or unicity of the Empirical Risk Minimizer guaranteed?

In Supervised Machine Learning, it is common to learn a target function by minimizing a (regularized) Empirical Risk Objective, i.e., for a dataset of $n$ samples $(X_i,y_i)$, the learned function $\...
4 votes
2 answers
270 views

Forecast Time Series like data

I have time series like data, 500 data points of (x,y) pairs. Where x = time in seconds and y = signals. Each of this candidates have an additional label (which ...
0 votes
0 answers
15 views

Embedding extraction -> Classifier VS Embedding learning+ Classification on-the-fly?

I have two questions: How should we compare in general which of the following perform better? I have a graph and would like to perform a graph classification task. Is it better to extract graph ...
2 votes
2 answers
116 views

Is machine learning all about hyperparameter tuning?

I understand the view that ML is a big optimization problem where we are trying to minimize the loss function and achieve the most optimal solution given the input. To achieve that we are feeding a ...
  • 141
1 vote
1 answer
38 views

Binary classification supervisor definition help

I need help with defining the supervisor for a ML model. Background: I’m predicting if a customer will respond positively to a marketing campaign. The response is a binary variable that I am given at ...
0 votes
2 answers
71 views

Can there be such things like supervised learning in bayesian approach?

Whenever I encounter articles on supervised learning examples are things like regression, classification, object detection, which are obviously ones following frequentist approach. I've recently ...
  • 111
1 vote
0 answers
37 views

How to interpret the supervised contrastive loss

I am currently trying to wrap my head around the supervised contrastive loss introduced in the following article : https://arxiv.org/pdf/2004.11362.pdf The loss formula in question is : $$Loss = \sum_{...
  • 11
0 votes
1 answer
261 views

Which LSTM output should be used for predictions?

Using this question as background: https://stackoverflow.com/questions/71023822/lstm-multi-variate-multi-feature-in-pytorch I was wondering how one processes the output of a pytorch LSTM I was using ...
  • 3
1 vote
0 answers
139 views

What is the best approach: Labeled training data and unlabeled test data [closed]

I'm new into the data science world and I am working on improving my knowledge so here is my problem: I want to build a binary classifier with the following constraints: I have 2 files training.csv ...
0 votes
0 answers
20 views

Question about proof in DAGGER algorithm paper

I'm new to imitation learning and trying to read a paper of DAGGER algorithm (https://arxiv.org/pdf/1011.0686.pdf). When reading the paper, I got stuck at proof of Theorem 2.2. This is a beginner's ...
0 votes
0 answers
7 views

Sample Selection within motion planning data

The target of this study is to attempt to learn behavior of an unknown algorithm from raw data. The environment in use is a 2D motion planning environment. We assume the algorithm behaves similarly to ...
  • 101
1 vote
1 answer
31 views

Bootstrap validation with a categorical outcome: should I sample each outcome separately?

I am doing something like what rms::validate does: bootstrap data frame rows in a supervised learning problem, fit a model to each bootstrap sample, apply that ...
  • 35.4k
0 votes
0 answers
24 views

Introduce a new variable to GLM

I have this one interview question regarding GLM model and would love some insights into method/product sense/common sense input. -Consider this car insurance pricing model: y (car price) = B1 * ...
1 vote
0 answers
24 views

Can a Supervised Routine be Compared Against an Unsupervised?

Just a question out of curiosity. Suppose that I had generated: (1) an unsupervised decision tree using 'interpretable clustering,' and (2) a second supervised decision tree (whether CART, or a ...
  • 234
0 votes
0 answers
187 views

How to calculate the bias b in support vector machine when the dual coefficient alpha is obtained?

For my example, I have two data points x = {(54001.988, 19999), (30021.983, 15000} and their labels are y = {1, -1}. I calculated the dual coefficient(Lagrange multipliers) alpha = {10000, 10000}. The ...
1 vote
1 answer
32 views

Limit of Momentum Update Equation

I am self-studying on optimization algorithm on https://d2l.ai/chapter_optimization/momentum.html and couldn't get my head around some derivation: Instead of the standard gradient descent update ...
0 votes
0 answers
37 views

How to train a model to maximize the difference of correlations?

I have two labeled datasets, $A$ and $B$: $(X_A, y_A)$ and $(X_B, y_B)$. $X_A, X_A \in \mathbb{R}^{m \times n}$ and $y_A, y_B \in \mathbb{R}^n$. $m$ is the number of features, $n$ is the number of ...
  • 31

1
2 3 4 5
13