Skip to main content

Questions tagged [machine-learning]

Machine learning algorithms build a model of the training data. The term "machine learning" is vaguely defined; it includes what is also called statistical learning, reinforcement learning, unsupervised learning, etc. ALWAYS ADD A MORE SPECIFIC TAG.

Filter by
Sorted by
Tagged with
2 votes
1 answer
75 views

Predicting cost for several options and then choosing the cheapest option

I created an ML model that predicts the cost of shipping an order in our online store. For each order placed, there is a variable number of methods (up to 10) available to ship. So for one order, ...
rimsky's user avatar
  • 23
0 votes
0 answers
17 views

derivative of Logistic Regression with sigmoid func [duplicate]

I am having difficulty figuring out, why I get different answer from the professor. we are tasked with finding the deriative of the logistic regression cost function with the sigmoid function: $$L(w│D)...
Ofek nourian's user avatar
-1 votes
0 answers
59 views

How to make triplet loss more separable?

I use triplet learning and triplet loss to learn embeddings from images to tell at inference if two face pictures are same or different person (my real problem is different but it cannot be disclosed ...
Przemek B's user avatar
1 vote
0 answers
29 views

Unacceptable results for adj R2

I have a dataset with 19 features. When I ran it with the Lasso algorithm. R2 for test and train was 0.69. But the value of adj r2 for test is 1.28 (above 1), and for train the value is 0.28. What is ...
Erfan Mollai's user avatar
2 votes
0 answers
49 views

derivative of Logistic Regression (sigmoid) [closed]

I am having difficulty figuring out, why I get different answer from the professor. we are tasked with finding the deriative of the logistic regression cost function with the sigmoid function: $$ L(w│...
Ofek nourian's user avatar
1 vote
0 answers
42 views

Optimal performance measures for species distribution models with presence and pseudo-absence data

I am currently building species distribution models (SDMs) (or ecological niches) using machine learning algorithms to predict the potential spatial distributions of animal species based on ...
Pierre Levoisin's user avatar
0 votes
0 answers
17 views

Reproducing PCA results of pca.fit_transform() using pca.fit()? [duplicate]

I have a data frame called data_principal_components with dimensions (306x21154), so 306 observations and 21154 features. Using PCA, I want to project the data into 10 dimensions. As far as I ...
george1994's user avatar
0 votes
0 answers
21 views

What dimensions to expect of Principal Components Analysis? [duplicate]

In both Python and R, the matrix of eigenvectors of Principal Component Analysis (PCA) is a matrix of principal components with dimensions (Number of Observations x Number of Principal Components). ...
george1994's user avatar
0 votes
1 answer
62 views

I am getting 98% to 100% accuracy in my logistic regression classifier on different seeds. Is it supposed to happen(mainly concerned about 100% acc)

My data split: ...
Haaki's user avatar
  • 1
0 votes
0 answers
28 views

Is Bootstrapping Independent Time Series to Construct Prediction Intervals Valid?

Question: I have a dataset consisting of multiple univariate time series, each representing an independent sequence of insurance claim amounts over time. My goal is to predict future claim amounts ...
Brandon_33's user avatar
0 votes
0 answers
9 views

Can manual feature extraction be considered a part of a learning algorithm?

We can view a learning algorithm as a tuple $(\mathcal{H}, \mathcal{O}, \mathcal{L})$ where $\mathcal{H}$, $\mathcal{O}$ and $\mathcal{L}$ are the hypothesis class, optimizer and loss function ...
ado sar's user avatar
  • 477
1 vote
2 answers
34 views

Is duplicating dataset an augmentation?

For a very small dataset, there is a lot of overfit in the random forest regressor model. I have removed extraneous data, scaling and feature selection, but overfit is still there. The oversampling ...
Erfan Mollai's user avatar
4 votes
1 answer
175 views

Motivation for automated variable selection in case of p>n

I have written the following text as a motivation for using automated variable selection in cases where the number of variables (p) is greater than the number of observations (n). However, I am not ...
george1994's user avatar
1 vote
1 answer
36 views

How reasonable is it to divide an offset by an integer to make the model non-singular?

I have been trying to fit a GLMM (Poisson) into a dataset which has flock size as response variable, climatic data as fixed effects, and different Zoos in the USA as random effects. I am a novice in ...
Rahul's user avatar
  • 23
0 votes
0 answers
38 views

Evaluating Lasso's Unique Solution and its consequences in applications?

I've grasped from a paper (https://www.stat.cmu.edu/%7Eryantibs/papers/lassounique.pdf) that Lasso may not yield a unique solution when the number of variables (p) exceeds the number of observations (...
george1994's user avatar
0 votes
0 answers
12 views

Log-likelihood calculation for unigrams

I am calculating the log-likelihood for each unigram that I generated by using the CountVectorizer to see each unigram's importance. However, I got all the positive value after calculating the log-...
Nick's user avatar
  • 1
0 votes
1 answer
37 views

Manual selection of parameters and features and bad results by gridsearch

For a very small dataset that I have, when I set the parameters with the help of gridsearch, the test and training results are not acceptable at all and have a huge difference. I have to manually ...
Erfan Mollai's user avatar
0 votes
1 answer
28 views

Why does increasing model complexity reduce bias over the entire data distribution?

In ML, we often talk about the bias-variance tradeoff, and how increasing model complexity both reduces bias and increases variance. I understand why increasing model complexity reduces bias at first, ...
user35734's user avatar
  • 406
0 votes
0 answers
48 views

Behavior of Lasso Estimator with More Predictors Than Observations (p > n) and Identical Correlations?

What is the behavior of a Lasso estimator if it is used in a dataset with more predictors (p) than observations (n), where all predictors are uncorrelated but highly relevant to 𝑦 y with exactly the ...
george1994's user avatar
3 votes
1 answer
38 views

Taking into account a non-symmetric loss function in a classification problem

Consider a binary classification method that estimates the class probability and where the observation weights can be specified (e.g. Logistic Regression). To accommodate the difference losses from TP ...
James's user avatar
  • 2,742
1 vote
1 answer
66 views

How to improve a model with little dataset? [duplicate]

I have a dataset that has 20 features and 65 samples. I did data scaling. I also did feature selection in different ways. But this is the result. ...
Erfan Mollai's user avatar
0 votes
0 answers
32 views

What is the difference between estimating parameters via MLE versus minimizing deviations from expectation?

What is the difference between estimating parameters using MLE (or MAP with uniform priors): $$\theta^* = \arg \max_\theta p(X|\theta)$$ and estimating them according to which setting would engender ...
actinidia's user avatar
  • 145
2 votes
1 answer
23 views

Precision calculation for Test data

I have a trained multiclassification (4 different labels) ML model for which I calculated Accuracy and Precision using Confusion Matrix . Now for the developed model, I give some test data without ...
Pavithra 's user avatar
0 votes
1 answer
20 views

How does KNNImputer stores fitted values of the train set?

If someone here is familiar with the KNNImputer implementation of Scikit-learn, I would be eager to learn this from him. When you fit an Imputer transformer on your ...
Yann's user avatar
  • 43
0 votes
1 answer
34 views

How to approximate the point a sequence is converging to?

I have created a poker solver as part of my Master's Thesis. This solver uses Counterfactual Regret Minimization (CFR) to compute a Nash Equilibrium of Hold'em or Omaha Poker. The solver uses existing ...
Timon Groen's user avatar
0 votes
0 answers
22 views

What methods to use for statistical analysis of a network structure?

I have a network structure (adjacency matrix) and want to find a method that tells me which features of my network are most important to explain my response variable. In this case its an infection ...
Nitara Wijayatilake's user avatar
1 vote
1 answer
50 views

Scaling Out-of-Sample Forecasts in a Model with Normalized Variables: Reverting to Original Scale

I'm working on making forecasts using a model where variables were scaled by $$ \tilde x_i = \frac{{x_i - \text{mean}(x_i)}}{{\text{sd}(x_i)}} , $$ and I've saved the mean and standard deviation. Now,...
george1994's user avatar
1 vote
0 answers
32 views

What to do when you realize you've overfit?

This is hypothetical and I would like to hear what people do when the get to the test set and realize they've overfit. Of course, preventing overfitting in the first place is ideal. You're working on ...
user2330624's user avatar
0 votes
0 answers
14 views

How to split data when training and tuning the meta learner in stacking?

I have a simple yet tricky conceptual question about the data splitting of a meta learning process. Assume I have a simple X_train, ...
Yann's user avatar
  • 43
1 vote
0 answers
26 views

Multiple Imputation for Missing Outcome Data

I have spent an extensive amount of time trying to understand the possible role of MICE in helping to "fill in" missing outcome data. I am relatively new to both multiple imputation and ...
R Har's user avatar
  • 11
1 vote
0 answers
26 views

Statistically determining a count of particles

I perform experiments to do measurements on various pharmaceuticals. One such measurement is interested in the number of particles which is confined into a small volume. The raw data in my experiment ...
gokudegrees's user avatar
0 votes
0 answers
13 views

Comparing GLMs with different fitted distributions

I have a scenario where I need to compare some generalized liner models (with same link function, target variable, but not necessarily nested) with k fold cross validation, using a cost function to ...
user101874's user avatar
2 votes
1 answer
83 views

We have sensitivity-specificity space (ROC curves) and precision-recall space (PR curves, $F_1$ score). What work has been done with PPV-NPV space?

Receiver-operator characteristic (ROC) curves display the balance between sensitivity and specificity: how good you are at detecting category $1$ (sensitivity) while not falsely identifying category $...
Dave's user avatar
  • 64.8k
0 votes
0 answers
13 views

How to determin the theoretical prediction limit for a complex process?

how can we find out what is the theoretical prediction limit for a complex process? For example, for a coin toss (on average) the prediction limit is 50%, that is we cannot predict better than this ...
vzografos's user avatar
1 vote
0 answers
29 views

What is the best way to use Gaussian Processes to approximate highly non-stationary functions?

Gaussian process regression has trouble approximating functions with "kinks". So, what is the most widely used method to deal with this problem? I have found many proposed methods, including ...
Dan Zhao's user avatar
2 votes
1 answer
32 views

Are there strategies for measuring accuracy of Euclidean distance-based similarity without ground truthing?

I have subjects with about 200 features each. These feature vectors are stored in a vector database, where similarity searching with Euclidean distance is used to find subjects that are similar to a ...
T_d's user avatar
  • 23
0 votes
0 answers
19 views

Why is my accuracy fluctuating for a while and then stuck? [duplicate]

I am building a cnn classifying model to predict images over 3 classes. The data is balanced, with 10.5k images for train ( 3.5k for each ), 3k validation images ( ...
Dragos123's user avatar
3 votes
1 answer
25 views

What is "clall" in index.Gap in "clusterSim" R package?

I am using the "clusterSim" package in my project (https://cran.r-project.org/web/packages/clusterSim/clusterSim.pdf, page 39) and I do not understand the meaning of the "clall" ...
user2702's user avatar
1 vote
1 answer
18 views

Input on methodology for analysing publicly available medical datasets

I'm being asked to analyse a publicly available medical dataset of adverse drug reactions. My data quality is quite sparse to begin with, so I've been trying my best to extract something meaningful ...
Mman231000's user avatar
0 votes
1 answer
61 views

Z-score and standard error in linear regression

I am reading Elements of statistical learning, and in the chapter on linear regression, I cannot understand the following: We have estimated the regression parameters $\beta_1, ..., \beta_p$ from $N$ ...
ge0rg's user avatar
  • 13
0 votes
0 answers
7 views

How to find a linear decision boundary of a linearly separable problem with unlimited class evaluations?

I have a binary classification problem, where my goal is to find a linear decision boundary (which I assume exists). The context of the problem is that I have an iterative optimization process, where ...
oskar0711's user avatar
3 votes
1 answer
69 views

What probability distribution is learned in this specific case? [duplicate]

I keep reading papers and blogposts where the training of a neural network is defined as learning some underlying probability distribution of the data. Imagine that you write CNN that outputs whether ...
Mah Neh's user avatar
  • 174
0 votes
0 answers
25 views

Avoiding Information Leakage in Backtesting with CPCV-Tuned Hyperparameters

I'm using Combinatorial Purged Cross-Validation to tune hyperparameters for a binary classification model applied in a month-end trading strategy. I have 6 months of data and used CPCV with 15 splits ...
June's user avatar
  • 1
2 votes
0 answers
38 views

Mathematical Introduction to Theory of Time Series Analysis

Assume that the reader has strong background in stochastic calculus (including and beyond continuous time stochastic processes like martingales and Markov chains and others, the construction of Levy ...
3 votes
0 answers
31 views

What are the "tricks" in machine learning? [closed]

I have come across a few different "tricks" in machine learning methodology, which I list below along with my rudimental understandings. The Kernel Trick: This is used in Support Vector ...
camhsdoc's user avatar
  • 409
0 votes
0 answers
24 views

Can we use convnets to learn the masked letter in a word?

I'm interested in training a CNN to learn the relationship between a word with a single masked letter and that masked letter. For example, if my model is $M$ and the input is "he-lo", it ...
Spencer Gibson's user avatar
1 vote
1 answer
121 views

Non-linear kernel for classifying data points corresponding to two concentric circles [closed]

Have seen article, while doing self-study, on Non-linearly seperable problems, here. The images as given there are here, and here. It deals a common text-book problem, where the data points are in two ...
jiten's user avatar
  • 113
0 votes
0 answers
15 views

Generalised Jensen-Shannon Divergence - Unequal Length Probability Distributions

I'd like to implement a generalized Jensen-Shannon divergence (GJSD) style test comparing 3 different probability distributions. In this respect, I looked at the Philentropy library in R with the ...
EB3112's user avatar
  • 244
3 votes
1 answer
98 views

Interpretation of a decision tree plot

For a paper, I am training different models and using LIME to simplify the blackbox models into a transparent decision tree model that I can visualize with view(tree, "mode", "graph&...
Tino D's user avatar
  • 268
8 votes
2 answers
550 views

Pearson correlation as a metric for the quality of regression models

A paper I saw used the Pearson correlation together with MSE to measure the performance of a machine learning model. After doing some research, I have seen that using Pearson correlations to evaluate ...
Degers's user avatar
  • 103