Logo
Video lesson: Supervised vs Unsupervised Learning — neural network diagram on dark background
11:45
22:10

Supervised vs Unsupervised Learning

In this lesson, we draw the fundamental distinction between supervised and unsupervised learning paradigms. You'll understand when to apply each approach, the role of labelled data, and how common algorithms fit within each category.

Lesson objectives

  • Define supervised and unsupervised learning with concrete examples
  • Identify the role of labelled vs unlabelled datasets
  • Map common algorithms (SVM, k-means, PCA) to their paradigm
  • Understand semi-supervised and self-supervised learning as extensions

Code snippet from this lesson

from sklearn.linear_model import LogisticRegression
from sklearn.cluster import KMeans

# Supervised: requires labels (y_train)
clf = LogisticRegression()
clf.fit(X_train, y_train)

# Unsupervised: no labels needed
kmeans = KMeans(n_clusters=3)
kmeans.fit(X_train)