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
1 vote
0 answers
9 views

Problems using custom dataset using Minirocket classification [closed]

I'm working on a bigger school project, trying to classify timeseries measurements with Minirocket/Rocket. My trainingdata consists of a 1D matrix containing the measurements, and a seperate 1D matrix ...
Michael's user avatar
  • 11
2 votes
0 answers
18 views

Is it valid to exhaustively test all possible combinations of features to find the best combination?

I have about 1000 labelled observations from about 50 subjects responding physiologically under different situations and am trying to classify the situation (usually into three classes of roughly ...
user1596274's user avatar
0 votes
0 answers
34 views

How to read Normal Distribution and Expectation notations [closed]

I am reading the paper on diffusion models (Eq. 4) and came across this equation: $$q(x_t|x_0) = N(x_t; \sqrt{\bar{\alpha_t}}x_0, (1-\bar{\alpha_t})I)$$ Now, I am not sure how to read the normal ...
fatih's user avatar
  • 1
0 votes
0 answers
16 views

Modelling issue [closed]

If I have 14 photos with the relative attractive marks and each of these photos were asked based on 6 questions to see how these 6 variables affect the relative attractiveness, what should be the ...
Stat's user avatar
  • 1
0 votes
0 answers
18 views

Why are the prediction intervals for my DNN regression model horizontal lines?

I am working on developing prediction intervals for deep reinforcement learning. Therefore, I am following the instructions given over here. I ran a small example using a simple deep-learning model to ...
desert_ranger's user avatar
0 votes
0 answers
8 views

What to do with features causing data drift?

I dispose of labeled train data and unlabeled test data. I want to tune and validate a classifier on train data in such a way that it can have good performance on test. By conducting some ...
Yann's user avatar
  • 1
0 votes
0 answers
6 views

How is $K_p$ parameterized?

How is $K_p$ parameterized? Can you help me derive it, I am a newbie. This is my derivation, but it is different from the formula on the picture, can you help me?
user avatar
1 vote
0 answers
32 views

Predicting continuous variable based on curve

I have a dataset of a set of curves measured at different frequencies, so it is composed of curves as the figure below for example. My dataset has many more curves of course. A curve is associated ...
raygozag's user avatar
  • 613
0 votes
0 answers
11 views

What is the meaning of the output for rfImpute function? [closed]

...
Apai's user avatar
  • 19
0 votes
2 answers
77 views

Why do ML models learn probability distributions and why does it matter?

I'm aware that this question is quite silly, but I've done reading and coded NNs for quite a while now, studied backpropagation and so on. However, I don't think I ever understood what is the ...
Mah Neh's user avatar
  • 71
0 votes
0 answers
4 views

Clustering with Isolation Forest: choice of hyperparameters [closed]

I want to optimize my Isolation Forest model for anomaly detection (unsupervised) For the parameters max_samples, n_estimators what could be the best range over which I could search (In terms of data ...
Umesh's user avatar
  • 1
0 votes
0 answers
10 views

Improving GPU Utilization in LLM Inference System [closed]

I´m trying to build a distributed LLM inference platform with Huggingface support. The implementation involves utilizing Python for model processing and Java for interfacing with external systems. ...
Cardstdani's user avatar
0 votes
0 answers
25 views

Why does $L_1$ weight decay negatively impact adversarial training for logistic regression?

I am reading through the original paper on the Fast Gradient Sign Method (Explaining and Harnessing Adversarial Examples by Ian Goodfellow et. al). We define an adversarial example as: $$\tilde{x}=x+\...
hkj447's user avatar
  • 447
0 votes
0 answers
20 views

How can I integrate time in my Implicit Feedback dataset?

I'm working on a recommendation system based on Collaborative Filtering. Specifically, I've been looking at models such as NCF (Neural Collaborative Filtering) and SAR (Simple Algorithm for ...
umus's user avatar
  • 1
0 votes
1 answer
32 views

Reason for high MSE and negative R square value

I am getting really high MSE and negative R square value. Dataset: https://docs.google.com/spreadsheets/d/1moTZS_LgOn6d74NC44i9lVcWchj-abVx/edit?usp=sharing&ouid=100514649347129021200&rtpof=...
user avatar
0 votes
2 answers
69 views

Can I use Tanh before softmax?

I am researching the use of neural networks for binary classification tasks of financial data. The output result is two-dimensional, such as [[0.5,0.5], [0.1,09]]. In the case of only 2000 small ...
Mar7's user avatar
  • 1
0 votes
0 answers
51 views

Probability Intervals with Machine Learning [closed]

Goal: Find the interval where a probability really lies with [x]% confidence. Let's start with a non-predictive experiment. A coin toss. Heads or tails. We already know that in a fair game, the ...
stephenspcdmav's user avatar
0 votes
1 answer
17 views

How to interpret the results of a classifier when train/test method gives much better results than cross validated one?

I need your help to understand a situation where using train and test set produces perfect results (in terms of accuracy, precision, and recall) but when cross validation is used, the accuracy on ...
letdatado's user avatar
  • 345
0 votes
0 answers
24 views

Is it possible to train a neural network to feed into a Random Forest Classifier or any other type of classifier like XGBoost or Decision Tree?

I want to create a model architecture to predict future stock price movement as such: The Goal of this model is to predict if the price will go UP or DOWN within the next 3 months. I have tried a few ...
Evank's user avatar
  • 1
0 votes
0 answers
6 views

model (constraint) sale probability of properties

I am trying to model the probability of a sale of a (vacation rental) property depending and price, property features (quality, size etc.), space and time. I am doing this at daily grain and achieve ...
cs0815's user avatar
  • 2,245
2 votes
1 answer
31 views

How to deal with extremely small training dataset in machine learning? [duplicate]

I've around 100 rows of data with labels ...
zZzZ's user avatar
  • 49
1 vote
1 answer
137 views

How to deal with extremely small training data? [closed]

I've around 100 rows of data with labels ...
zZzZ's user avatar
  • 49
0 votes
0 answers
8 views

How to improve prediction quality of LSTM model

I am trying to train an LSTM-based model in MATLAB to predict 365 next values given 365 previous values of a time series. Input shape is (1000, 365) and output shape is (1000, 365) i.e. there are 1000 ...
Avnish Bansal's user avatar
-1 votes
0 answers
18 views

augmentation for small dataset [duplicate]

0 I have a dataset that is very small and for this reason it performs very poorly (65,20). How can I enlarge the dataset? I multiplied the dataset by a series of numbers and entered it into the main ...
Erfan Mollai's user avatar
0 votes
0 answers
54 views

Which statistical model will be best for this data?

I'm trying to identify the relationship between the dependent variable and the independent variables. I've utilized linear regression, but I'm not sure if it's suitable given the distribution of my ...
Chemokine1's user avatar
2 votes
1 answer
71 views

Compute R Squared by Fixing Betas for Multi Linear Regression without Intercept results in a large R Square

I want to fix the betas in multi linear regression based on some data I have, which leads to a RSquare value less than 0% and greater than 100 % based on the projection approach mentioned in ...
godimedia's user avatar
  • 121
-1 votes
0 answers
43 views

How can you formalize moving the decision frontier for predicting crisp class label in classification?

I am tackling a classification problem with 3 classes. I trained and validated few models, but their predictions are always skewed towards the majority class (I guess this is normal since imbalance is ...
Yann's user avatar
  • 1
4 votes
2 answers
515 views

Overfitting in randomForest model in R, WHY?

I am trying to train a Random Forest model in R for sentiment analysis. The model works with tf-idf matrix and learns from it how to classify a review, in positive or negative. Positive ones are ...
Anisa's user avatar
  • 43
3 votes
1 answer
50 views

How do I develop prediction intervals for Reinforcement Learning?

I recently learned about the concept of prediction intervals (for regression) and I would like to apply them to my Deep Reinforcement Learning algorithm. I am working with a Model-Free RL algorithm ...
desert_ranger's user avatar
0 votes
0 answers
9 views

EWMA formula for SGD with momentum different than generic EWMA formula

I am currently trying to understand how SGD with momentum works, what I understand is it uses the Exponential Weighted Moving Average concept to make the updates smoother. We take weighted average of ...
learnToCode's user avatar
1 vote
0 answers
14 views

An error occurred when using the xgboost as a classifier for hiclass [closed]

Bellow it's my example when using the xgboost classifier for hiclass. My question is specifically directed to the hiClass Python package for hierarchical classification. I would like to model the ...
Ramzy's user avatar
  • 21
0 votes
0 answers
10 views

Can anyone explain me what does ACF and PCF tells from this figure?

I want to know what does it mean? Is my data stationary or not because the p value tells its stationary and what should be the order ARIMA model(p,1,q) is it (p,d,0) or (0,d,q)
theunknown's user avatar
0 votes
0 answers
20 views

Can a Catboost oblivious tree split on the same feature more than once

When training an oblivious decision tree in Catboost, can it use the same feature more than once for splitting? Let's say there is a feature age. If the first split ...
NotProbable's user avatar
0 votes
0 answers
15 views

Choosing spatial resampling functions for species distribution modeling study with different pseudo-absence sampling methods

I am conducting a species distribution modeling study using machine learning models. Since I only have presence data, I have employed various pseudo-absence sampling methods, including random ...
Marine Régis's user avatar
0 votes
0 answers
7 views

Activation functions in Neural Cellular Automata

NCAs aren't necessarily the exact same as neural networks but I am trying to do my own implementation to understand better. Do activation functions (especially in this case) serve only for training or ...
ra111's user avatar
  • 1
0 votes
0 answers
14 views

How do I interpret a Random Forest Survival C-index value relative to the Requested performance error?

I'm doing a random forest survival analysis for a school project and I'm confused about the C-index output that I'm getting relative to the Requested performance error. Shouldn't my C-index get higher ...
Jake S's user avatar
  • 21
1 vote
0 answers
8 views

PCA time series Index in R: Score Plot Doesn't Match Expected Index

I'm working on creating a PCA Index in R to understand how it works. I've used 'make up' data for this purpose. However, when I plot the scores of the first component, the results are not as expected. ...
searchandprint's user avatar
0 votes
0 answers
15 views

Strange Variance Term for Normal Prior $w^2\sigma^2$

I've attached two screenshots, one with the question and one with the answer. It seems to me that the prior is wrong and it should include $w^2$ not $w^2\sigma^2$ I apologise for, including such a ...
CormJack's user avatar
  • 161
1 vote
0 answers
34 views

Violation of i.i.d assumption in time series modeling

In time series forecasting,let's say you have $x_1, x_2, x_3, \cdots, x_t$ and the goal is to predict the the value of $x_{t+1}$ given values at previous times $1,\cdots,t$. Let's assume that the ...
Quqnus's user avatar
  • 11
6 votes
1 answer
27 views

What is happening behind the scenes when we use CalibratedClassifierCV without prefit?

From what I understood by reading sklearn Probability Calibration, when we run CalibratedClassifierCV we will fit "a regressor (called a calibrator) that maps the output of the classifier (as ...
andy mot's user avatar
0 votes
0 answers
11 views

Synthesizing multivariate time-series data with generative models for multiple data

I am new to multivariate time-series data and am particularly interested in synthesizing such data using generative models like TimeGAN: TimeGAN. From reading the literature on this topic, I have ...
user3178756's user avatar
1 vote
0 answers
51 views

Causal forests for causal interaction effects between two treatment factors

I'm analyzing a survey experiment data with a factorial design with $2 \times 2$, where each factor is randomly assigned with equal probability. I'd also like to know the heterogeneous effect of the ...
Jin's user avatar
  • 11
0 votes
0 answers
22 views

Derivation of the Marginal Likelihood for Gaussian Processes

In this post a derivation of the marginal likelihood for Gaussian process regression is given. This is the most detailed derivation of the marginal likelihood for GPR I have seen so far. There are, ...
MLEnthusiast's user avatar
0 votes
0 answers
24 views

Predicting Winner of the Euro 24 using Machine Learning

I have the following question. I would like to predict the results and thus also the course of the Euro 24 with machine learning, but I don't know which method is best suited for this. Basically, I ...
manofthousandnames's user avatar
2 votes
2 answers
43 views

Point Biserial vs. Spearman Correlation

I am playing around with the Spambase dataset from UCI also in the bayesreg R package (4601 instances). The target is a binary ...
LennyBruceIsNotAfraid's user avatar
1 vote
2 answers
30 views

KNN K = 1 Training on itself vs K > 1

When training a $KNN$ algorithm, why is that with $K = 1$, the model trains using the "1 nearest observation to each training point" and treats this as itself resulting in a training error ...
CormJack's user avatar
  • 161
0 votes
1 answer
27 views

Is softmax the same as vector normalization in 3D graphics?

I just found out about the softmax function in machine learning. It creates even probabilistic distribution out of a vector of numbers, which means that all numbers up to 1. It sounds a lot like the ...
jcubic's user avatar
  • 103
0 votes
0 answers
35 views

Logistic Regression - 2 different Independent variable's dummies have perfect correlation

Let's say I have 2 variables in my model: Credit_Card_Debt - with the dummies 'No credit cards','0-100','101-1000','1000+' - 1000+ is the reference category Number_of_credit_cards - with the dummies '...
Mobix's user avatar
  • 1
2 votes
3 answers
49 views

Is relying on just the confusion matrix for highly imbalanced test sets to evaluate model performance a bad idea?

I have a binary classification model with a test set that is highly skewed, the majority class 0 is 22 times greater than the minority class 1. This causes my Precision to be low and Recall to be high,...
statsnoob's user avatar
0 votes
0 answers
38 views

Should I interprete data as noise or not

I am tackling a classification problem with 3 classes. Here is what those classes look like on the Two first principal axes. I fine-tuned a SVM model and the best performance achievable was 50%. By ...
Yann's user avatar
  • 1

1
2 3 4 5
403