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
0 votes
0 answers
16 views

CNN classifier for cytometric data always has a similar accuracy, regardless of complexity, number of epochs or size of the layers [duplicate]

Background: I am making a convolutional neural network (CNN) to try and classify cytometric data. This data has a shape (num_cells, num_markers). Additional ...
Viktor VN's user avatar
  • 101
1 vote
1 answer
21 views

Impute missing value [closed]

In machine learning when I impute missing values which of the following I perform : 1-Impute data set and then split it? 2-Split dataset to Training and testing datasets and then Impute each datasets ...
zhyan's user avatar
  • 335
0 votes
0 answers
27 views

Rationale for box-constrained optimization in adversarial example search

In Section 4.1 of "Intriguing properties of neural networks" by Szegedy et al., the authors define the optimization problem they solve to find adversarial examples in a deep neural network. ...
synack's user avatar
  • 371
0 votes
1 answer
33 views

Making a multiclass classification problem binary during data preprocessing vs using a multiclass classifier

Sometimes you have a problem that presents as a multiclass problem in your data, but you only care about the result of a binary classification. E.g. you have a manufacturing process which can result ...
Grumpy's user avatar
  • 3
1 vote
1 answer
64 views

Comparing glmnet models part 2

I'd like to compare performance between two models that use different sets of predictors. I'm trying to implement what Roland suggested I did in his answer: ...
locus's user avatar
  • 1,553
6 votes
2 answers
822 views

How to incentivise AI to make risky predictions

I'm trying to build a weather forecasting AI. I have a dataset that contains the peak temperatures for each day. I have trained it with MSE as the loss function and it has worked fairly well. I do ...
n-l-i's user avatar
  • 193
0 votes
0 answers
44 views

Identifying states (or clusters) in multivariate mixed-type time series

I have multivariate time series with mixed data types, which includes continuous variables, binary variables, and variables with bimodal distributions. I need to identify distinct states or epochs in ...
graavit's user avatar
0 votes
0 answers
31 views

Derivation of EM algorithm for Gaussian mixture

I am going through Expectation Maximization (EM) algorithm derivation for Gaussian Mixture models. I understand it except for a small detail. So, the general idea of EM is to maximize the expectation ...
baronett's user avatar
0 votes
0 answers
7 views

Which model to use for word tokenization?

What type of model for word tokenization in a group of words is good?? I want to tokenize skills in a group. There are multiple groups, and I want to predict group number using a single skill. I have ...
bunny's user avatar
  • 1
6 votes
2 answers
255 views

Hierarchical forecasting - demand classification required for prediction?

I have product sales data for which I would like to predict what will be the sales for each product at the product level, product store level, product store and region level etc. To solve this problem,...
The Great's user avatar
  • 3,232
2 votes
0 answers
33 views

Hierarchical forecasting packages - No trend removal or stationary check?

I have sales data for which I would like to predict what will be the sales for each product at the product level, product store level, product store and region level etc. To solve this problem, I came ...
The Great's user avatar
  • 3,232
0 votes
0 answers
17 views

in-sample error and the optimism

I'm currently reading p228 of The Element of Statistical Learning, which covers training error, in-sample error, and optimism. Let me quote some of the textbook contents as follows. The $Y^{0}$ ...
jason 1's user avatar
  • 257
0 votes
0 answers
16 views

How can I compare model performance across datasets of varying sizes?

I have a person wearing 2 sensors. I create two models, one using Sensor-1 and other using Sensor-2 data I have multiple people repeating the same experiment with varying numbers. How do I a ...
Darpit's user avatar
  • 31
1 vote
0 answers
24 views

Why is the concept of RKHS useful in kernel ridge regression?

The way I have seen kernel ridge regression introduced is as follows. Given data $(X,Y)$ you want to fit a function $f$ from a RKHS $\mathcal{H}$ to minimise some empirical loss $\sum_i L(f(x_i), y_i)$...
Danny Duberstein's user avatar
0 votes
0 answers
31 views

Can someone explain how the lambdas in lambdarank work?

I am reading From RankNet to LambdaRank to LambdaMART: An Overview. Section 4.1 describes LabdaRank. The last paragraph on page 8 and first paragraph of page 9 describe how the score ($s_i$) of each ...
Abhay Gupta's user avatar
0 votes
0 answers
43 views

statistics and probability textbook for data science and machine learning [duplicate]

I want to learn statistics and probability for machine learning and data science, and I'm don't know what textbook I should use for self-study. Now my choice is between The Elements of Statistical ...
2 votes
0 answers
148 views

Why is cross-entropy increasing with accuracy? [closed]

I'm making an implementation of the softmax regression and I'm struggling to understand the nature behind the problem of increasing value of Cross-Entropy: $H(y_i, p_i)=-\sum_{i=1}^C y_i log(p_i)$, ...
JoshJohnson's user avatar
1 vote
0 answers
34 views

mixed effect model question

Hi i have a certain task i want to solve: For two months, participants played an app, in which they played 5 different therapeutic games (TGs). At the beginning of each session, they also completed a ...
nof's user avatar
  • 11
0 votes
0 answers
3 views

Loan Data: Bucket recoveries 1-D array

Some context: When someone defaults on their loan, we keep track of the recoveries as a percentage of the exposure (loan amount), we have a limited time T (legally) to collect recoveries, those ...
FaresDjerourou's user avatar
1 vote
1 answer
42 views

Sklearn Gaussian Process Regressor Overfitting

I am testing a set of regression algorithms and I'm having troubles with GPR. I have a set of 60 observations x 101 variables as a predictor (X) versus a set of 60 observations x 1 variable as a ...
Mutewinter's user avatar
0 votes
0 answers
32 views

How to determine which variables are the most important to define each cluster from a Hierarchical clustering analysis, using R

After searching, reading posts, and trying to solve this issue myself for several days, I think it's time to ask for help. I'm performing a Hierarchical Clustering analysis on a dataset, that includes ...
JLLavin's user avatar
0 votes
0 answers
8 views

Why detections count is not equal to unique truth count in YOLOv4 test result report?

I trained model using YOLOv4 on GPU, CUDNN and openCV (python) with AlexeyAB\Darknet with multi-label on windows environment. These labels are 25 classes (from 0 to 24). Then I test the model and I ...
N.white's user avatar
5 votes
1 answer
60 views

Multiclass proper scoring rule decomposition: (weighted) average across the categories?

I have found a Python function that calculates the decomposition of various proper scoring rule, such as Brier score and log loss. However, it does not seem to accept arrays as arguments, so if I want ...
Dave's user avatar
  • 61k
1 vote
0 answers
31 views

Which book help us to do the best EDA for data science? [closed]

I am new at data science. I would like to make ML models in orde to make predictions, but I am lost when I have to make interpretations to data... I would really like to understand the data with ...
3 votes
1 answer
50 views

Analogue of landscape conjecture in likelihood theory or Bayes?

The so-called landscape conjecture in machine learning says that in high dimensions, most critical points of the loss surface are saddle points rather than poor local minima. Out of curiosity I was ...
Durden's user avatar
  • 1,205
1 vote
0 answers
14 views

Is There a Standard Metric for Evaluating Treatment Impact Considering Action Cost in Uplift Models?

I'm currently exploring Uplift modeling, specifically the use of the Conditional Average Treatment Effect (CATE) metric: $$ \tau(t', t, x) := \mathbb{E}[Y | X=x, T=t'] - \mathbb{E}[Y | X=x, T=t] $$ ...
Amit S's user avatar
  • 37
2 votes
1 answer
117 views

How to interpret the deviance plot by boosting models

This plot is taken from a gradient boosting regression example in the scikit-learn documentation. What does deviance mean? How should this plot be interpreted? In which case do we have over/...
Mykola Zotko's user avatar
0 votes
0 answers
31 views

How to interpret error histogram and scatter plot?

I'm new to machine learning and I'm having a hard time interpreting how good my model is performing. I have run my model on a dataset of wine attributes trying to predict alcohol content based on the ...
n-l-i's user avatar
  • 193
0 votes
1 answer
30 views

Relation between number of classes, their separability and classification difficulty

Intuitively, it seems that a classification problem with more classes is "harder" than the same problem with fewer classes. However, this also seems to depends on the separability of the ...
Aethor's user avatar
  • 1
3 votes
2 answers
198 views

How to combine two linear models?

I am trying to predict housing prices using as few variables as possible. One way that yielded the best results so far is splitting the data into two data-sets ($houses < 100m^2$ and $houses >= ...
Anton's user avatar
  • 31
5 votes
1 answer
209 views

Regression coefficient on a triangle using geometry

I am encountering a question as follows: Let $X, Y$ be two independent uniform random variable on $(0,1)$. We consider the regression model $Y = \beta_1 X + \beta_0$, given the restriction that $X + Y ...
mathdoge's user avatar
  • 153
1 vote
0 answers
29 views

Given conjugate prior and posterior distributions, what is the PRIOR predictive distribution? [closed]

I am doing an assignment on my statistics class. We had 1 lecture about bayesian parameter estimation, where we were taught about the following formula (and it's discrete form, if $h(\theta)$ was ...
ampersander's user avatar
6 votes
2 answers
189 views

As Brier Score = MSE, does MSE in a regression have a calibration-discrimination decomposition?

When the outcome of a supervised learning problem is binary and probabilities are predicted, Brier score can be decomposed into a measure of calibration and a measure of discrimination. ...
Dave's user avatar
  • 61k
2 votes
1 answer
74 views

Could classical astronomic discoveries be made using ML?

Imagine that prior to the time of Copernicus, scientists could run machine learning algorithms (somehow). Would it be possible to discover the truth of the geocentric model with their use? Would the ...
Sam's user avatar
  • 515
2 votes
0 answers
18 views

Looking for a way to train a model to learn optimal parameters/hyperparameters of clustering

I have 5000 docs, each is a review. For each review, I'm plotting the sentences in a semantic dimension. Now, I'm applying clustering to these points for each review. The success of my model depends ...
Prithvi's user avatar
  • 21
2 votes
1 answer
82 views

Regularization Problem and Reproducing Kernel Hilbert Space

The following shows part of the page 169 of The Element of Statistical Learning that I want to make clear. We have $$\min_{f \in \mathcal H_K}[\sum_{i = 1}^NL(y_i, f(x_i)) + \lambda\Vert f\Vert_{\...
jason 1's user avatar
  • 257
0 votes
0 answers
12 views

Time Series Prediction for Variable-Length Input with Fixed Sampling Period

I'm working on a time series prediction task where I need to predict the parameters (amp, phase, freq, offset) that best fit a variable-length input series. The samples are always at the same period. ...
Andrea Arlotta's user avatar
1 vote
1 answer
51 views

Relative Risk or Odds ratio using machine learning

I am thinking of using machine learning type classification models to compare them with the traditional approach of logistic regression (dichotomous outcome) in a sample of patients with diabetic foot ...
ronald's user avatar
  • 57
0 votes
0 answers
134 views

Bert Used for generative AI

I have a doubt regarding using "Bert" as a generative model. I know Bert can be used for classification or fine-tuning the question-answering. However, is it possible to use Bert to generate ...
Encipher's user avatar
  • 175
0 votes
0 answers
87 views

Is the right set of customers to use in my churn model?

I am creating a churn model in python. The full dataset has around 90k records stretching back many years. I'm using a subset of the full dataset. This subset only includes clients where we've worked ...
jabs's user avatar
  • 127
1 vote
1 answer
81 views

How to predict outcome with zeros, and both negative values and positive values in ML model?

My Outcome is quarterly sales, which is right_Skewed and the range of it is large b/c different groups purchased differently. For Example, there are lots of groups that made zero or less than 10 ...
user401029's user avatar
3 votes
0 answers
89 views

Is Brier score strictly proper in multi-label problems?

In problems where one of $3+$ categories can be observed and we prodict the probability of each category being observed, it is known that the Brier score is a strictly proper scoring rule that is ...
Dave's user avatar
  • 61k
0 votes
0 answers
24 views

Bias-Variance tradeoff proof [duplicate]

why are y_hat and ε independent? I think ε dose effect y_hat
Yangge Hu's user avatar
0 votes
0 answers
19 views

Does Positional Interpolation Change Llama's Architecture?

I'm currently exploring Meta's positional interpolation method, which aims to increase the context size in their large language model. This method extends the context length from n x n into n′ x n′. ...
user219313's user avatar
1 vote
1 answer
134 views

Help with Classification model for S&P500

I have started a project in order to develop my coding skills, where I am predicting next month's S&P500 return direction based on some macroeconomic and financial variables. These datasets have ...
user199's user avatar
  • 13
0 votes
0 answers
16 views

what does edge mean in the context of sample space?

This is a follow-up question on this post It uses a term 'edge'. For example, it says I understand that extrapolation is harder than interpolation. And I understand that if we choose a point to ...
Sherlock_Hound's user avatar
0 votes
0 answers
11 views

Should unprocessed features be kept in the dataset along engineered ones?

I'm working on a Machine Learning classification problem that has five Service Spending features (among many others) in its dataset, each sample is a customer. For instance, here are the first three ...
spengler's user avatar
0 votes
0 answers
26 views

Reporting internal validation from .632 bootstrap in caret

I am developing Machine learning prediction models using the caret package in r (Elastic net, SVM, Random Forest, XGBoost). I have 650 cases with 104 having the event of interest. Instead of splitting ...
Dwayne T's user avatar
0 votes
0 answers
62 views

How do I proof or disprove that the size of a document influences classification accuracy?

I have a multinomial Naive Bayes model that classifies a document into 1 of 178 classes. This goes well about 50% of the time, so it's pretty good (for my use case) considering the large set of ...
Jordy Weening's user avatar
0 votes
0 answers
17 views

Conditional Average Treatment Effects: What is the logic underlying using the covariates to predict the residualized scores?

I've consulted a few references, including this online book, and I've got a good grasp on using double machine learning to estimate ATE after debiasing/denoising the treatment variable (T) and the ...
C McNorgan's user avatar

1
3 4
5
6 7
403