Questions tagged [classification]

An instance of supervised learning that identifies the category or categories which a new instance of dataset belongs.

Filter by
Sorted by
Tagged with
1
vote
1answer
20 views

Clusterize Spectrum

I have pandas table which contains data about different observations, each one was measured in different wavlength. These observsations are different than each other in the treatment they have gotten. ...
2
votes
2answers
88 views

How can I label (predict) an unseen set of data based on an existing model?

I'm working on a learning multi-label classification project, for which I've taken 16K lines of text and kind of manually classified them achieving around 94% of accuracy/recall (out of three models). ...
0
votes
1answer
21 views

[under/over]-sampling teaches model the wrong distribution?

TLDR: Will under/oversampling during the training phase teach the model the wrong distribution and adversely affect accuracy? Let us assume you want to train a classifier to differentiate between ...
1
vote
0answers
29 views

Clustering time series data using dynamic time warping

I would like to cluster/group the curves in the attached picture with Python. The data is already normalized and my approach would be to use dtw (dynamic time warping) to calculate the distance and ...
1
vote
4answers
33 views

Train a model using multiple data sources

I have to train a classification model to predict if a customer will buy a product or not. I have multiple (eg. 3 or 4) data sources. The variable distributions among the different data sources is ...
0
votes
0answers
38 views

Sampling methods for Text datasets (NLP)

I am working on two text datasets, one is having 68k text samples and other is having 100k text samples. I have encoded the text datasets into bert embedding. ...
-1
votes
1answer
32 views

Equivalence of two separate data distribution

I am working in generative modelling. I have a real dataset of which I want to know the underlying distribution. For this I create a synthetic data generator which tries to mimic the real data. I ...
0
votes
2answers
23 views

Creating dataset - imbalanced or balanced?

I'm trying to make an image classification model and I have 5 classes - A, B, C, D, E. The goal is to get the highest possible classification accuracy. I have a database of images and I'm selecting ...
0
votes
1answer
44 views

Identify “steady-state” time series window

I'm new with the time-series analysis. I have several time-series (noisy of course) part of the same set of measurements (sampled simultaneously). The time series are the results of a stochastic ...
6
votes
2answers
204 views

significance test and sample size estimation for classifiers

What is the test to tell if e.g. an F1 score of 0.69 for classifier A and 0.72 for classifier B is truly different and not just by chance? (for mean-values one would use a "t-test" and ...
4
votes
3answers
266 views

Reducing the size of a dataset

I am trying to classify gestures. I am using Python's scikit learn library classification algorithms for that. I have collected depth images for this purpose. 200 samples are collected for each ...
0
votes
2answers
28 views

Is it bad to have a lot of one class of Data [K-NN classifier]?

I am trying to train a sklearn K-NN classifier on a labeled text dataset (in Irish). There are 5 classes, 0-4, but there is a lot of variation between how many there are in each class. What I have ...
0
votes
0answers
13 views

Cross entropy and function approximation

My overall question is: the universal approximation theorems can provide a good heuristics on defining the loss function for supervised regression problems, i.e., because universal approximation ...
0
votes
0answers
12 views

Manually tune tf-idf features in document classification

I am working on a multi-label document classification task with a very small data set (180 labeled documents) and a fairly large number of labels (20). I found that - ignoring label correlations and ...
0
votes
0answers
16 views

Which scaler to use for combining different embeddings?

I am working on an experiment, where I am combining ( average and concatenate ) different embeddings like Elmo, Bert etc, since both embeddings are from different models, I thought, it's better to ...
1
vote
1answer
84 views

Problem understanding probabilistic generative models for classification

I am a student and I am studying machine learning. I am focusing on probabilistic generative models for classification and I am having some troubles understanding this topic. In the slide of my ...
1
vote
1answer
42 views

Encoding for classifiers

I have some doubts regarding encoding (i am not familiar with tasks like these) categorical variables in order to use them as parameters in a model like logistic regression or SVM. My dataset looks ...
0
votes
2answers
49 views

How to predict unknown unknowns in machine learning

I am dealing with a problem about classifying bird species through analysing MFCCs. I already built a dataset with 13 MFCCs for two kinds of birds. And I trained the data with Naive Bayes & KNN ...
0
votes
2answers
22 views

Selecting Transforms with sklearn pipelines

So I am currently working on a Data set, and I want to use Pipelines to select the transforms. Here is an example of what I want to do : ...
1
vote
3answers
57 views

How to combine two different embeddings in the best way possible?

I have two models which are giving two books embedding Ml_model_a => book1_embedding [ 1, 200 ] Ml_model_b => book2_embedding [ 1, 200 ] I am building a ...
2
votes
1answer
80 views

Making sense of loss and accuracy curves

This is an issue that I have come across over and over again. Loss (cross-entropy in this case) and accuracy plots that do not make sense. Here is an example: Here, I’m training a ReNet18 on CIFAR10. ...
1
vote
0answers
31 views

Prediction in CART Decision Trees

I was studying the algorithm of CART (classification and regression trees), but the formula of the prediction is irritating me. First we have the following definition: Let $X:={x_1,...,x_N} \subset \...
1
vote
2answers
50 views

Low precision on classification model

I am working since some months on a prediction from lead to a sale. Someone makes a lead on my website and I want to predict if this user will make a sale. I have these metrics on the test data. Now ...
1
vote
0answers
11 views

How to compute a confidence interval for AUC?

I found that in results of several binary classification problems, people report an AUC value together with a CI. I wonder how those CIs are computed. Is there a close-formed formula to compute them ...
-1
votes
1answer
33 views

Train a model to determine that the probability of an event given a set of features is higher than when given a different set of features [closed]

I have a data set of attempted phone calls. I have a set of features, say, hour of day, and zip code. I have a label indicating whether the callee picked up the phone or not. I want a model to predict ...
0
votes
0answers
39 views

Spoken utterance classification on RAVDESS using MFCC

I am planning to classify two audio files in which different sentences are spoken. Don't want to do speech to text as on prem speech to text conversion models are not good, and don't want to go to ...
0
votes
1answer
74 views

Good test accuracy but poor confusion matrix results

Ive trained a model to classify 4 types of eye diseases using MobileNet as the pretrained model. I achieved a test accuracy of 94%, but when I look at the confusion matrix, it seems like it isn't ...
0
votes
0answers
10 views

Majority of feature maps of CNN are black

Assuming we have a following CNN : Conv->MaxPool->Conv->Maxpool->Linear. What does it mean - intuitively - if the majority of the feature maps of the first convolutional layer are black i....
3
votes
1answer
103 views

How to classify a new email as spam/not spam?

I am working on a small exercise for determining if an email is spam or not. My dataset is the following: ...
0
votes
1answer
31 views

What kind of neural network is the best for classifying a series of vectors

I am currently working on a project where I decided that it might be useful to use machine learning. I have a good understanding of pytorch and I know how to build my neural network within this ...
0
votes
0answers
16 views

Some Confusions Regarding Variable Importance Extraction of Several Machine Learning Models

I'm trying to apply several machine learning algorithms in R using caret (decision trees, ensemble methods (bagging, boosting, ...
0
votes
1answer
33 views

Predict Ethereum price up or down by given Bitcoin price

How would you proceed, if you have 2 parameters, for example, the price of the Bitcoin and the price of Ethereum for each day and you want to predict based on the Bitcoin price if Etherium will go “up”...
2
votes
2answers
35 views

Predicting financial data (choosing a model)

it is my first time doing something with financial data. I have a dataset with account numbers and some other information about each client (some clients span more than one row since we have info for ...
4
votes
1answer
44 views

Why Does XGBoost Keep One Feature at High Importance?

I am training an XGboost model for binary classification on around 60 sparse numeric features. After training, the feature importance distribution has one feature with importance > 0.6, and all the ...
1
vote
1answer
27 views

Is it better to have one model with more categories or less with two for multi-label classification?

For classifying text into three classes question, complain and complements where each sample can have multi-labels (question and complains, question and complements): is it better to have one model ...
0
votes
2answers
28 views

Is it possible to reuse my CNN trained model over a new dataset with different number of classes?

I had used a trained CNN model (VGG16) over a large dataset with 6 number of classes in FC layer it gave me a good accuracy ( for example over Testing data: loss=0.59, accuracy=0.829). When I had ...
0
votes
1answer
19 views

How does TF-IDF classify a document based on “Score” alloted to each word

I understand how TF-IDF "score" is calculated for each word in a document, but I do not get how can it be used to classify a test document. For example, if the word "Mobile" occurs ...
1
vote
1answer
28 views

Imputing features with NA values in classification task

I currently have a dataset where each observation is a person's traffic ticket history over districts. For each column, which represents a district: 1 represents that a person has received 1+ traffic ...
0
votes
0answers
32 views

Formulate Confusion Matrix from Precision Score

I have the precision scores from 5 classes. Is it possible to create the confusion matrix from that scores. While running the code, I only saved those precision values by mistake. So now I want to ...
0
votes
1answer
26 views

What should I do to test the confidence of my deep learning model?

I've recently fine-tuned a deep learning framework/model BERT for a sentiment classification task. I had a 80/10/10 train/validation and test set. After running several experiments, I've gotten a ...
0
votes
1answer
56 views

Getting 0 accuracy and NaN mae for all epochs training my NN

Background: I made a simple game using python library 'Turtle' in which there is a long plank with a ball balanced on top of it. I can press right or left arrow keys to rotate the plank (either ...
0
votes
0answers
39 views

Dot product as template matching with a linear classifier(cs231n)

I'm not sure I understand something from this article: https://cs231n.github.io/linear-classify/ In the context of linear classification of images, it is written: Interpretation of linear classifiers ...
0
votes
1answer
28 views

How to create a classification model for multi output dataset?

I have a dataset where there are two target variables target-1 and target-2. Both target variables are ordinal and thus I want ...
0
votes
0answers
29 views

Why the training loss increases, and predict everything as '1' or '0'

Those two pictures are from two similar experiments using same code. I am fine-tuning a pretrained-Bert model to do a binary text classification task, the dataset is 50% positive vs 50% negative, so ...
1
vote
1answer
21 views

Preparing Dataset Minority Class vs Majority Class

I'm currently doing a binary classification for sentiment prediction. Currently I have the majority class (~90% of the data) as my positive class (labelled 1) and the minority class (~10% of the data) ...
1
vote
1answer
76 views

Comparing multi-class vs. binary classifiers in predicting a single class

I've pretty much read the majority of similar questions, but I haven't yet found the answer to my question. Let's say we have n samples of four different labels/...
0
votes
0answers
56 views

questions about logistic regression

In the following Linear Regression discussion I didn't understand a few things: So my questions are: In the third slide: What does this probability means $P\left(y_i|x_i\right)$ and accordingly what ...
1
vote
0answers
63 views

Assign more importance to recent records during training

My goal is to build a classification model in order to predict if a customer will buy a product or not (binary classification). Since in the last months (let's say 3-4) I know that the advertising of ...
1
vote
0answers
23 views

Choosing the best set of features when forced to choose M out of N available features

Given: N features that map to some label Y using a Neural Net(NN)- it's a classification problem. Problem: I want to get away by using only a subset of features denoted by M, where M<N. Now I am ...
0
votes
0answers
32 views

Binary classification of multiple Sequences using Keras

I am trying to classify multiple independent sequences using Keras. My data looks like this (example with different stocks and their values). ...

1 2 3
4
5
48