Computer • Chapter 16

Machine Learning

Machine Learning
Concept • History • Types • Algorithms • Evaluation Metrics • Applications • Practice MCQs
Introduction to Machine Learning
  • Machine Learning enables computers to learn from data and make decisions.
  • The chapter frames ML around History, Algorithms and Applications.
  • The source later summarizes that Machine Learning is transforming industries worldwide.
English Summary
Machine Learning enables computers to learn from data and make decisions. This chapter covers its history, types of Machine Learning, algorithms, evaluation metrics and applications.
Types of Machine Learning visual
Source-derived visual: three learning types listed in the PDF.
History of Machine Learning
Machine Learning history timeline
Timeline built only from the dates and milestones stated in the source.
Period / YearSource milestone
1950Alan Turing introduced the Turing Test.
1959Arthur Samuel coined the term machine learning in 1959, associated with his work on learning checkers programs.
1980s–1990sNeural networks evolved.
2000s–presentDeep learning revolution.
Types of Machine Learning
Supervised Unsupervised Reinforcement Learning
Classification exactly follows the three categories shown in the source.

Supervised Learning

Uses labeled data to train models.

Examples: Linear Regression, Decision Trees, SVM.

Unsupervised Learning

Finds hidden patterns in data.

Examples: K-Means Clustering, PCA.

Reinforcement Learning

Uses rewards & penalties to learn.

Examples: Q-Learning, Deep Q-Networks.

Exam Trap
K-Means is placed under Unsupervised Learning in the source; Q-Learning is under Reinforcement Learning.
Machine Learning Algorithms
Machine Learning algorithms and metrics
Algorithm groups and evaluation metrics from the source.
GroupExamples listed in source
RegressionLinear regression
ClassificationLogistic regression, Decision Tree, Naïve Bayes
ClusteringK-Means, Hierarchical
Neural Networks & Deep LearningListed as an algorithm area in the chapter.
Evaluation Metrics

Regression Metrics

MSEMAER² Score

Classification Metrics

AccuracyPrecisionRecallF1-score

Applications of Machine Learning
Applications of Machine Learning
The four application areas named in the PDF.

Healthcare

Named as an application area.

Finance

Named as an application area.

E-commerce

Named as an application area.

Autonomous Vehicles

Named as an application area.

MCQs for Practice
Q1
Who coined the term “machine learning” in 1959?
Source answer: Arthur Samuel.
Q2
What type of learning is K-Means?
Source answer: Unsupervised.
Q3
Which listed algorithm is commonly used for spam classification?
Source answer: Naïve Bayes.
Conclusion in source
Machine Learning is transforming industries worldwide.
Machine Learning is transforming industries worldwide.
Quick Recall
Core Idea
Machine Learning → Learn from Data → Make Decisions.
TermRecall cue
1950Alan Turing — Turing Test.
1959Arthur Samuel coined the term machine learning in 1959, associated with his work on learning checkers programs.
SupervisedLabeled data.
UnsupervisedHidden patterns; K-Means, PCA.
ReinforcementRewards & penalties; Q-Learning, Deep Q-Networks.
RegressionLinear regression.
ClassificationLogistic regression, Decision Tree, Naïve Bayes.
ClusteringK-Means, Hierarchical.
Regression metricsMSE, MAE, R² Score.
Classification metricsAccuracy, Precision, Recall, F1-score.
ApplicationsHealthcare, Finance, E-commerce, Autonomous Vehicles.
Exam Trap
Supervised = labeled data; Unsupervised = hidden patterns; Reinforcement = rewards & penalties.
Exam Trap
Arthur Samuel coined “machine learning” in 1959. Despite its name, logistic regression is commonly a classification algorithm.