Questions tagged [classification]
Statistical classification is the problem of identifying the sub-population to which new observations belong, where the identity of the sub-population is unknown, on the basis of a training set of data containing observations whose sub-population is known. Therefore these classifications will show a variable behavior which can be studied by statistics.
6,885
questions
1
vote
1
answer
542
views
Can you help me to understand this deduction for proving Naive Bayes is a Linear Classifier?
In this tutorial on Naive Bayes Classififer in section 1.1, the author proved naive bayes is a linear classifier.
Consider binary classification where $y=0$ or $1$. Our classification rule with ...
1
vote
1
answer
206
views
Should I balance my training dataset for an employee attrition analysis in machine learning?
I need to perform an analysis on employee attrition using Machine Learning algorithms. I intend to do both Supervised Learning ...
1
vote
0
answers
32
views
How can we best utilize the knowledge of P(y=1) in classification? [duplicate]
Premise
I saw an interesting example of a machine learning logistic classifier for modeling/predicting sentiment for customer reviews. One of the first things in the example was a note on ...
1
vote
0
answers
199
views
Extract features from a questionnaire
I am using the answers from a questionnaire for a classification problem.
I discovered that a question can have nested sub-questions..
Let's say that I want to predict the age of a student based on ...
1
vote
1
answer
98
views
Temporal Distance Intervals Classification Task
I was reading a paper Playing hard exploration games by watching YouTube https://arxiv.org/abs/1805.11592.
By my understanding the authors use convolutional neural networks to generate embeddings ...
1
vote
1
answer
19
views
Training a classifier on 2 catalogs combined
I'm currently trying to train a machine to identify flashes of light in the sky as supernova (SN) or not. To do this, I'm combining 2 different catalogs:
A big catalog (99% SN) with brighter flashes ...
1
vote
0
answers
10
views
Classify a specific object amongst other diverse objects
I have a device which takes one picture per day of a slab. It contains many instances of a specific object (let's call it "Object A") and a few other objects (let's call them "Others").
I want to ...
1
vote
0
answers
119
views
why the kernel size become greater as the spatial size of feature map goes down in inception network?
In the inception networks like inception-v3 and inception-v4, the kernel sizes are smaller in the lower layers,such as 3*3, but in the higher layers, the kernel sizes seem to be larger,such as 5*5,7*7,...
1
vote
0
answers
47
views
How to evaluate the performance of a predictor on an unlabelled dataset? What is an appropriate test set size and how to sample it?
I am working on a project with goal to deduplicate a customer database. We don't have any annotations (no training/test set with the ground truth values).
We implemented multiple unsupervised ...
1
vote
0
answers
57
views
Discriminant Analysis: Explicitly writing Covariance matrix given some sample data
Let $(X, Y) \in \mathbb{R}^d \times \{0, 1\}$ give a random pair wherein the conditional distribution of $X$ given $Y$ is $X | Y \sim \mathcal{N}(\mu_Y, \Sigma_Y)$, $\mu_0 \neq \mu_1 \in R_d$, where $\...
1
vote
0
answers
210
views
Performance of classifier with positive, negative, and unlabeled data
The problem
I have a dataset where ca. 90 % of the dataset is unlabeled and the rest is positively and negatively labeled (unbalanced).
I want to describe the performance of a classifier on this ...
1
vote
0
answers
36
views
Multilabel classification versus yes/no classification for each class (with label priority)? [duplicate]
NOT A DUPLICATE. These questions are related, but mine is asking about a specific application of classifiers - flagging Stack Exchange posts. I want to know which of the 2 methods is most effective ...
1
vote
2
answers
284
views
Cluster analysis with boosting models for better predictions?
let's say that we have a simple, binary classification problem (with many predictors and many observations) and want to fit for example some kind of boosting algorithm to obtain resutls. Let's also ...
1
vote
1
answer
38
views
Get test and traininig data set by using cross validation
I have a data sets and want now find a model to predict wages.
I read that just cutting the data sets into 2 parts by a percentage number to get the training and test data set is not efficient. ...
1
vote
0
answers
104
views
Aggregating factors: dummy vs. relative frequency
I have a dataset that looks like this:
...
1
vote
0
answers
79
views
A better way to compare accuracy?
Hi I have an algorithm that takes a single sample, call it i and tries to predict what other samples in a cohort it is most closely related to. This cohort consist of N=11K from different tissues. ...
1
vote
0
answers
40
views
Appropriate statistical or machine learning measure to find important IDs within array of t-tests
I have an array of data that contains ~600 protein name identifiers, and each ID holds an accompanying four hundred t-test scores from interrelated experiments. So it's a 600x400 matrix, let's say.
I'...
1
vote
0
answers
28
views
How to Optimize Predictive Classification Model for Lead Time
How do I optimize a predictive classification model to reward variables and values that give predictions earlier in sequential data?
For example:
Let's say I'm modelling whether an upcoming ...
1
vote
0
answers
58
views
Statistical difference of machine learning predictions
I am applying a machine learning classification method to two difference scenarios for my boss (in this context, I am using a random forest). Due to the nature of the problem, there is high class ...
1
vote
0
answers
71
views
Classification/Prediction based on Multivariate Time Series
So, I have a time series with many independent variables (X's) and an outcome variable Y (that I want to predict, think a 2 class logistic regression where output would either be 1 or a 0). Kindly see ...
1
vote
0
answers
31
views
Adding new samples to dataset
Consider the situation where we have a trained classifier (which isn't dramatically over/underfitted) that we want to improve, and lots of unlabeled data readily available, and we would like to spend ...
1
vote
0
answers
166
views
Great ways to identify adult content in text
What are some good ways to identify adult content in text. It is definitely a text classification problem, but how do we handle words that are spelt like @$$.
1
vote
2
answers
222
views
PCA variances pattern changed greatly after data cleaning
I have data, when I normalize it and then performed PCA, I calculated the variance of PC components, I found that, the first component is 72% and seconed component is 8% (total 72+8=80%) and so on.
...
1
vote
0
answers
2k
views
How to do one-class classification?
I am working on a classification model for crop detection. Let say I have the data of wheat only. I want my classifier to recognize its pattern and after providing a new data set, it should tell me ...
1
vote
0
answers
50
views
Best labelled dataset for training a binary image classifier
I want to train some binary classifiers in Keras (e.g. to decide if there is person on a picture or if there is a vehicle on it). What is the best dataset to use for this? I mean datasets like these. ...
1
vote
1
answer
94
views
Decting new classes (open world classification)
In real world applications very often the entire set of classes is not known during the training phase (e.g. identifying objects, sounds, etc.). A system is needed that can classify observations into ...
1
vote
0
answers
34
views
Fingerprint at scale - what is the state of the art?
I'm working on a problem of fraud detection in account opening. When a new user opens an account, we compare a set of three fingerprints against entries in an existing database.
The existing database ...
1
vote
0
answers
318
views
Log loss when classes are -1 and +1 [duplicate]
We can calculate the log loss for a classification problem with two classes as follows:
where y is the label of the actual class and ...
1
vote
0
answers
42
views
What are some potential reasons for no significant difference between Random Feature Selection and Automatic Feature Selection?
Basic info abut the experiment:
Binary classification of exons
10 fold cross validation
1200 features of exons are ranked by Fisher Score, Relief and Gini Index feature selection algorithms
1-...
1
vote
0
answers
482
views
Multi-label classification, binary loss concerns
I am solving a multi-label audio classification task with neural networks. The dataset is comprised of 10 classes, and the input data to the network are audio files where two of these classes are ...
1
vote
1
answer
89
views
Neural Networks: How to do class prediction from murky labels
I'm conducting an experiment with the MNIST digit data - handwritten digits 0-9, each example composed of 28x28 bitmap of pixels.
Imagine a collection of examples is drawn at random without class ...
1
vote
0
answers
49
views
Optimal Parameter for Binary Classifier
If I have a binary letter classifier for the letter "I" which classifies using the sum of all pixels in a picture. The parameter that is input to the classifier decides its classification.
MATLAB CODE:...
1
vote
0
answers
45
views
CART selection and *deselection* classification tree
I came across a line in Peterson, et al. (2016) that says:
The specific settings applied in the rpart procedure ensured that only the largest subgroup would be ...
1
vote
0
answers
502
views
Weight minority classes using XGBoost (Multiclass)
I'm dealing with a multiclass problem in R using XGBoost. The dataset has 3 Classes representing the following proportion: 20% - 75% - 5%.
Given the description above, it would be awesome some tips ...
1
vote
0
answers
139
views
Multi-label classification with Neural networks
Task:
Multi-label classification of sounds using neural networks. (Urbansound8K Dataset)
Problem:
How to best generate my combined dataset, considering maximum 2 sounds combined at the same time.
...
1
vote
0
answers
787
views
Training of multiple time-series with different lengths
I have a lot of time series with different lengths. I would like to know what are the best practices to fit them to a Bidirectional LSTM model. The problem is a Binary Classification of Sequence to ...
1
vote
0
answers
94
views
Splitting Data Into Training and Test set
I am trying to split a data set into training and test set with these codes
...
1
vote
0
answers
86
views
logistic regression with two-sided covariate
I want to do a logistic regression, with multiple covariates, where at least one of the covariates is two-sided. When I say that a covariate $x_1$ is "two-sided", I mean that values close to the mean ...
1
vote
0
answers
254
views
How can I use real valued labels in training a CVAE?
The Conditional Variational Autoencoders (CVAE) (and other classification networks) I have come across use a one hot vector encoding for labeling categorial data sets.
In my case, I do not have a ...
1
vote
0
answers
32
views
Information Gain and attributes
In the book i'm reading about Data Mining, in the chapter about decision tree it's said that the information gain test is biased towards tests with many outcomes (attributes having a large number of ...
1
vote
1
answer
4k
views
Classification threshold selection for predictions on unseen data
In binary classification, what is the optimum probability threshold to predict binary outcomes (0/1) on unseen data without knowing the actual outcome?
Let's assume that a random forest model has ...
1
vote
0
answers
19
views
Classification using an ensemble of decision trees
I am going through some theory regarding classification using multiple decision trees. Note that a tree has probabilities of classes on each of its leaves . Here's the equation:
P(y' = $\omega$ | x', ...
1
vote
0
answers
243
views
Multi-label classification: overlapping or graph structure among labels
I am doing multi-label text classification. I have 5000 classes and there is a graph structure among these classes.
How to deal with multi-label classification where there is overlapping or graph ...
1
vote
0
answers
2k
views
Classification with 500 Categories
Currently I am working on several projects with classification algorithms. The number of categories is very high (between 100 and 4 000, but let us assume it is 500).
Which algorithms are suitable ...
1
vote
0
answers
715
views
Classification on multivariate time series
My dataset:
121 individuals characterized by a categorical variable let’s say Y (so 121 values of Y)
for each individual, I have 5 time series, let’s say X1, X2, X3, X4, X5.
each time series contains ...
1
vote
0
answers
95
views
Bayesian framework for artificial neural networks in classification?
I am trying to understand the probabilistic concepts behind classification using neural networks, for the goal of incorporating prior information over the target class distributions.
I am failing to ...
1
vote
0
answers
94
views
Find a cost-sensitive multiclass algorithm
I am working on decision trees which can directly work in a multiclass context. My aim is reduce the misclassification's errors of a decision tree by improving its ability to tackle imbalanced ...
1
vote
0
answers
420
views
Optimal value for the intercept term in SVM
(note that this problem is different from this one, since the latter considers primal's Lagrangian)
Hi,
I am trying to figure out the SVM's dual problem. The primal problem is
$${\displaystyle {\...
1
vote
0
answers
699
views
Optimal degree and C parameter in Polynomial SVM
Okay I know that there are a lot of posts out there about the C parameter in SVM, but I had a quick question about this.
In Polynomial SVM (Which I'll be coding in Python), I can set the parameters ...
1
vote
2
answers
1k
views
What is monotonic classification?
I read this about student surveys:
Student surveys occupy a central place in the evaluation of courses at
teaching institutions. At the end of each course, students are
requested to evaluate ...