Classifying email as spam, labeling web pages based on their context, voice recognition are the example of which of the following?

Correct option is C

Supervised learning is a machine learning approach in which a model learns from a dataset containing input examples along with their corresponding known labels or target outputs. The objective is to learn a mapping that can correctly predict the output for previously unseen inputs.
Spam email classification learns to distinguish between spam and legitimate messages using labeled examples, while web-page classification can assign predefined categories based on labeled training data. Similarly, voice recognition systems can learn to map audio signals to known words or commands using labeled speech samples.
Information Booster
1. Classification in Supervised Learning
· Classification predicts a discrete or categorical class label for an input.
· Examples include:
· Spam / Not Spam
· Relevant / Irrelevant webpage
· Recognized word / command
· The model learns the decision boundary from previously labeled training examples.
2. Regression in Supervised Learning
· Regression predicts a continuous numerical value rather than a class.
· Examples include:
· Predicting house prices.
· Forecasting temperature.
· Estimating product demand.
· Thus, supervised learning includes both classification and regression tasks.
3. Typical Supervised Learning Algorithms
· Decision Tree
· Support Vector Machine (SVM)
· k-Nearest Neighbors (k-NN)
· Naïve Bayes
· Artificial Neural Networks
· Logistic Regression
4. Training Process
· A labeled dataset is divided commonly into training and testing sets.
· The model learns patterns from the training data.
· Its performance is then evaluated on unseen test data.
· Common evaluation measures for classification include accuracy, precision, recall, and F1-score.
5. Real-World Applications
· Email spam detection.
· Image and object classification.
· Speech/voice recognition.
· Sentiment classification.
· Medical diagnosis based on labeled clinical data.
Additional Knowledge
· Option (a) Reinforcement Learning — Incorrect: Reinforcement learning involves an agent interacting with an environment and learning through rewards or penalties. Examples include game playing, robot control, and sequential decision-making.
· Option (b) Shortest Path Algorithm — Incorrect: A shortest-path algorithm is a graph algorithm used to determine a minimum-cost path between vertices. Examples include Dijkstra's algorithm, Bellman–Ford algorithm, and Floyd–Warshall algorithm. It is not a machine-learning paradigm.
· Option (d) Unsupervised Learning — Incorrect: Unsupervised learning works with unlabeled data and attempts to discover hidden structures or patterns. Common tasks include clustering, dimensionality reduction, and association-rule learning.
· Key distinction:
· Supervised → Labeled data → Predict known target
· Unsupervised → Unlabeled data → Discover hidden patterns
· Reinforcement → Rewards/Penalties → Learn actions or policies