WBJECA 2025 — Computer PYQ

In machine learning, algorithms are generally categorized based on whether they require labeled data (Supervised) or unlabeled data (Unsupervised).

• Supervised Learning: The algorithm learns from a training dataset where inputs $X$ are mapped to known outputs $Y$. The goal is to learn a function $f$ such that:

  $$f(X)\approx Y$$

  • Naïve Bayes, SVM, and Decision Trees are all classic examples of Supervised Learning algorithms used for classification or regression.

• Unsupervised Learning: The algorithm works with unlabeled data, searching for hidden patterns or structures. K-means is a clustering algorithm that groups data points based on feature similarity without pre-existing labels. Mathematically, it aims to minimize the within-cluster sum of squares:

  $$\min \sum _{i=1}^k\sum _{x\in S_i}\Vert x-{\mu }_i{\Vert }^2$$

  Where ${\mu }_i$ is the mean of the points in cluster $S_i$.