Questions tagged [supervised-learning]

Supervised learning is the machine learning task of inferring a function from labeled training data. The training data consist of a set of training examples. In supervised learning, each example is a pair consisting of an input object (typically a vector) and a desired output value (also called the supervisory signal). A supervised learning algorithm analyzes the training data and produces an inferred function, which can be used for mapping new examples.

Filter by
Sorted by
Tagged with
0
votes
1answer
14 views

Will Different Types of Labels Affect Feature Engineering Outcomes?

Here I would like to limit the question to 2 supervised learning tasks: classification and regression. My question is: for a given set of raw training features, will feature engineering be affected by ...
0
votes
1answer
11 views

Extracting information from form document through supervised learning

I was searching for a while around the web and I couldn't find any solution that would give some ideas on how to solve my problem. I have a few hundreds of document with some permission forms filled ...
0
votes
1answer
8 views

Negative Latent Factors in Factorization Machines

I'm studing a specific implementation of a recommendation system leveraging on a factorization machine algorithm. For each person_id and item_id combination, I have an implicit rating of 1 or 0 ...
1
vote
0answers
13 views

Is a “decision boundary” incompatible with proper scoring rules?

Having a decision boundary in a binary classification problem tells me that if the point lies on one side of the boundary, classify as $0$; if the point lies on the other side, classify as $1$. What ...
4
votes
1answer
23 views

Is the regressor (sometimes called “independent” variable) actually independent of the response from a probabilistic perspective?

In supervised learning, we refer to the regressors as independent variables and response variables as dependent, but from a probabilistic standpoint, I am having trouble understanding this. To ...
1
vote
0answers
12 views

Modelling the probability of class membership using k-NN and associated distances

I have a Euclidean space in which observations of a similar class are close and usually non-intersecting. I use k-NN to then classify new samples. What I currently do is find the k nearest samples (L2 ...
1
vote
0answers
15 views

Classification technique to classify categories in two variables when dateset has larger number of numerical variables and few data points

I'm doing data analysis and need to build a classification model. Data set has 72 data points and 37 numerical variables Two categorical variables categorical variable 1 has two levels A and B ...
9
votes
4answers
2k views

Are all Machine Learning algorithms divided into Classification and Regression, not just supervised learning?

I'm newbie in AI I know that Supervised Learning algorithms are divided into Classification and Regression algorithms. But is that true of all machine learning algorithms, not just Supervised Learning?...
0
votes
0answers
8 views

Reverse engineer unsupervised algo using supervised one

Let's say that through some unknown process, each row in a dataset is labelled with an integer between 1 to 10 inclusive. Now, if I run random forest for example, and get a promising result for ...
0
votes
1answer
15 views

What classifier could predict spam/ham labels for SMS messages better than Naive Bayes?

I have 7000 SMS messages, 6000 ham, 1000 spam. Typical messages are: ...
0
votes
0answers
14 views

Making predictions for existing observations for new input variable values

My dataset consists of a set of e-commerce products, where each observation corresponds to a particular product. My target variable is the number of purchases over a fixed time period of the given ...
0
votes
0answers
6 views

How to performe LDA on PC components in R?

I have a big dataset as 1025 FTIR spectra. They belong to 21 groups/class and have 632 features (or wavenumbers). Lets say 21 groups are 21 patient samples from which a set of spectra collected ...
0
votes
0answers
22 views

Which specific type of recurrent neural network (RNN) is required to solve this supervised sequence problem?

I have a variety of features and an sequence target variable of fixed dimension 1x20 e.g. [0,0,0,1,0,...]. I've been reading up on the potential of RNNs to predict sequences. What specific methods/...
4
votes
1answer
57 views

Is Anomaly Detection Supervised or Un-supervised?

AFAIK - One way to process data faster and more efficiently is to detect abnormal events, changes, or shifts in datasets. Anomaly detection, also known as outlier detection is the process of ...
2
votes
0answers
31 views

What are the signs of noisy labels in a dataset?

When learning a classification model in supervised machine learning, how can we test whether the labels in the dataset are noisy or not? Is there any particular way to check it or any specific sign to ...
0
votes
0answers
24 views

does the distribution of all independent variables in a dataset need to be normally distributed to perform data analysis on it?

For my project that looks at if debtors will repay, I have a positively skewed target variable (with non-normal errors) which contains many zero values (which is a problem in itself) but after reading ...
0
votes
0answers
15 views

Features of serverless functions that can be used in supervised learning

Which input parameters I can choose for the supervised machine learning for prediction of the response time of serverless functions? I thought about CPU and memory, but It is hard to get them from the ...
0
votes
0answers
11 views

What kind of supervised machine learning algorithm takes negative weights for instances?

Is there any algorithm deal with negative instance weight ? For gradient based method it’s tricky to have negative weights since negative would cancel out other instances ?
16
votes
3answers
1k views

(Why) Is absolute loss not a proper scoring rule?

Brier score is a proper scoring rule and is, at least in the binary classification case, square loss. $$Brier(y,\hat{y}) = \frac{1}{N} \sum_{i=1}^N\big\vert y_i -\hat{y}_i\big\vert^2$$ Apparently this ...
2
votes
0answers
59 views

Can any class of ML algorithms efficiently learn the modulo function (x mod y)?

The modulo operator is a non-smooth, non-linear function which has a kind of regularity that is easy to learn by human learners. Z = X % Y However, naive NN ...
1
vote
1answer
24 views

Feature selection by doing pairwise KS test between different features in a dataset

I am trying to build a supervised learning model (binary class) and I wanted to check whether the features belonging to the respective classes come from the same distribution or not. Because the ones ...
0
votes
0answers
19 views

Input with variable length Classification problem

I have a dataset with patient information with discrete labels (labels are stages of a particular disease) which needs to be predicted (Basically a classification problem). The data set looks ...
0
votes
0answers
19 views

Machine learning algorithm for finding most similar entries in dataset

I have a pandas Dataframe, which has data as structured below. ...
0
votes
1answer
52 views

How to improve predict performance using proxy to target signal?

I have a regression problem in a supervised learning setting. To put it formally, given an input x and a target y, I want to ...
1
vote
1answer
23 views

Is John Skilling's Nested Sampling Algorithm a Supervised or Unsupervised Learning Technique?

Is John Skilling's Nested Sampling a Supervised or Unsupervised Learning Technique? See https://en.wikipedia.org/wiki/Nested_sampling_algorithm.
0
votes
0answers
64 views

A method to separate classes while taking variable dependence into account

I have posted a question related to this problem over a year ago and we still were not able to figure this out. We have two groups, A and B that we want to train on to separate them. Both have ...
1
vote
0answers
22 views

Determine minimum data to start with building model

We have developed a basic Regression framework where we try to build models for over 100 configs(stored in a file). To run : ...
1
vote
0answers
11 views

What to do if you have two training samples with same features but different labels?

I'm curious to know what can be done in the case where two training samples have the same description but different labels. For example, the sample below: ...
1
vote
0answers
21 views

Best ML approach for anomely detection on structured text data

I need help trying to understand what ML algorithm (or at least family of algorithms) would be best for my problem. There seem to be a great many different approaches and no clear explanations of what ...
0
votes
0answers
14 views

When performing validation, should you also tune the number of hidden units and hidden layers?

I understand tuning the learning rate, momentum, batch size, etc. and finding the best set of parameters using the validation set. However, I don't understand when people say that you should also ...
1
vote
1answer
26 views

When designing a convolutional neural network, what do you actually have to calculate?

One thing that confuses me about CNN is that I cannot tell when something is designed based on calculation versus when something is (arbitrary) design choice (no need for calculation). My question ...
0
votes
0answers
15 views

Best supervised regression algorithms for purposes of smoothness and interpolation

Suppose I have a dataset -- in this case a time series dataset of dimension $m$ -- which is causal. When I say causal, I mean that, given a $t_0$, no data from time $t_i > t_0$ may be used to ...
3
votes
1answer
75 views

Classification of data tables (each table is an item)

I have to work on a binary classification task where single items to be classified are not single rows of a data matrix, but groups of rows. In other words, I have $N$ data tables of varying size $n_i ...
1
vote
0answers
22 views

what performance metrics is more important to comapre classifiers? [closed]

I have classified my biological data by using a few machine learning algorithms and calculated sensitivity, specificity, AUC, accuracy, kappa, PPV and NPV etc.? which one of these metrics are the most ...
0
votes
2answers
19 views

Bus transport prediction using LSTM

I have a dataset that contains information of the ppl who enters the bus in given stop in a day. The day is divided in 10 minutes gap, resulting in 144 samples per day. The data format is: (yday, wday,...
1
vote
0answers
146 views

We know that The empirical risk is an unbiased estimate of the risk. Then why Is the training error biased ? (How does to proof for the former break)

Setting: Let $S$ be a set of $m$ samples from a set $Z$ and $w^{*}$ be an arbitrary vector. (Samples Are I.I.D and we are operating in a binary classification setting) Then $\mathbb{E}_{S \sim D^{m}}...
1
vote
1answer
19 views

Why do model learn better on the same data copied few times?

I've faced something I can't understand. I am working with ANN, model is pretty simple, only few dense layers. As an input I have 8 columns with standarised values, problem is supervised learning, ...
0
votes
0answers
24 views

Time series binary classfication

Problem: Hi, I m a new machine learning practitioner. I have a dataset about hedge fund. It contains monthly hedge fund returns and some financial metrics. I calculated metrics for every month from ...
1
vote
1answer
23 views

How is the network connected in the following introductory tutorial of Pytorch?

I am going over the tutorial by Pytorch Here, they initialize a random input matrix $$x \in \mathbb{R}^{64 \times 1000}$$ which I am assuming each row of this matrix represents a $1 \times 1000$ ...
0
votes
1answer
70 views

Assumptions on the underlying function for a binary classification problem

Consider the binary classification problem, and let the feature space be denoted as $S$. What we are assuming is that there is an underlying function $F$, mapping from feature space S to the set ...
1
vote
1answer
30 views

Is there a clear relationship between number of training examples and over/underfitting when you do not know the model complexity?

It seems that without knowing the model complexity, it is difficult to state for certain what is the relationship between the number of training examples and over/underfitting. As a concrete example, ...
0
votes
0answers
13 views

Identify and correct mislabeled categorical data in supervised learning

I have game/player level football data in 230 dimensions and want to classify the likely position that each player was playing in each match. The data is labelled, however each player is classified ...
1
vote
1answer
44 views

(Reference request) What is the history of the “cross entropy” as a loss function for neural networks?

There seems to be a gap in the literature as to why cross-entropy is used. Older references on neural networks ("ANNs") always use the squared loss. For example, here is one from Chong and Zak "An ...
1
vote
1answer
13 views

After training an XGBoost classifier on a set of features, (how) can I use it to make new predictions based on one of those features?

Forgive me if this is a somewhat naïve question. I have trained an XGBoost classifier that uses COVID-19 patients' age, sex, location, etc. to predict their mortality risk (here is the dataset). The ...
2
votes
1answer
26 views

Underlying similarities between Knn and Least squares

It is mentioned in the ESL book Page 19, that Knn and Least squares end up approximating conditional expectation by averages. To explain the statements in detail, the book mentions 3 equations. The ...
2
votes
4answers
379 views

How to deal with incorrect labels in classification?

I have a dataset with 2 classes: A and B. The problem is that 20% to 30% of the samples of class B are mislabeled (labeled as B but the right label is A) and I am not able to identify those mistakes. ...
0
votes
0answers
21 views

Should I use Gaussian naive Bayes or Bernoulli naive Bayes?

My data set looks like following: I have 5 continuous columns in the data set: income, age, experience, money spent/month, and mortgage. I have 5 categorical columns: all categorical (1's, 0's and 2'...
0
votes
1answer
32 views

Classification learning curve: function of number of features

I have a binary classification problem where I am using linear SVM. I am interested in diagnosing underfitting/overfitting by visualizing learning curves. My models have different feature sizes; for ...
1
vote
0answers
32 views

Using cluster comparison metrics to evaluate a classification task

Suppose I have a multi-class classification task. As far as I can tell, the primary metrics used for evaluating performance on this task is either to compute the confusion matrix, or the per-class f ...
0
votes
1answer
19 views

What should I be careful when using the word “supervised” in paper writing?

I am a biologist using machine learning tool for my research. I modified matrix decomposition ($V \approx WH$) to fit my data and wanted to describe about that in my paper. If I fixed one matrix ...

1
2 3 4 5
11