A hospital wants to build a model that uses labeled X-ray images previously diagnosed by radiologists to determine whether a new chest X-ray image shows a lesion or no lesion. There was also a proposal to estimate the size of the lesion as a number, but the only requirement this time is the lesion or no-lesion determination. Which type of task is this?

1 / 1
Select an answer
CorrectA

Explanation

Question Overview

Choosing the type of task that predicts a category.

Requirements to satisfy
  • 1「shows a lesion or no lesion」The answer is a discrete category = classification task (a number would be regression)
Per-option explanation
ACorrect

Classification

Correct. Classification is a supervised learning task that assigns an input to a predefined category (discrete label). When the answer is a category, such as lesion or no lesion, the task is classification.

BIncorrect

Regression

Regression is a task that predicts a continuous number.

This question is about predicting a category, lesion or no lesion, so it is not regression, which predicts a number, and is incorrect.

CIncorrect

Clustering

Clustering is unsupervised learning that groups unlabeled data into similar groups.

This question is supervised learning that predicts the correct label, lesion or no lesion, and is not grouping, so it is incorrect.

DIncorrect

Dimensionality reduction

Dimensionality reduction is unsupervised learning preprocessing that compresses the features of data to make them easier to handle.

This question is a task that predicts a category, not feature compression, so it is incorrect.

Key Takeaway

Remember the differences among the four representative machine learning tasks.
・Classification: supervised learning that trains on labeled data and assigns an input to a category (discrete label) (for example, lesion / no lesion, dog / cat).
・Regression: also supervised learning, but it predicts a continuous number such as sales or temperature.
・Clustering: unsupervised learning that groups similar data without using labels (for example, customer segmentation).
・Dimensionality reduction: unsupervised learning that compresses features without using labels to make them easier to handle (used for visualization and preprocessing).
Identify them by output: category → classification, number → regression, unlabeled grouping → clustering, compression → dimensionality reduction.

Related Links