Assignment: Machine Learning and Artificial Intelligence (AI). Name: ____________
No. of Roll: ____________ Course Description: Instructor: ____________
Department / University: ____________
Date: ____________
1. Acknowledgement
Artificial Intelligence (AI) is the science of making computers behave intelligently. Computers
can learn patterns from data and make predictions or decisions without being explicitly
programmed for each rule thanks to the machine learning (ML) subfield of artificial intelligence.
This assignment explains key concepts, types of ML, common algorithms, the ML workflow,
applications, challenges, and future directions, with small examples from online shopping and
hospital OPD management.
Table of Contents
Introduction
AI vs ML vs Deep Learning
A Brief History Key Concepts in ML
Machine Learning Types Common Algorithms (Plain Overview)
The ML Workflow (Step by Step)
Real-World Applications Mini Case Studies (E-commerce & OPD)
Tools & Libraries
Challenges, Risks & Ethics
Future Trends
Conclusion
Glossary
References
1) Introduction
Artificial Intelligence aims to build systems that can perceive, reason, and act. Voice
assistants, recommendation systems, and self-driving features are all examples. Machine
Learning is a way to achieve AI: we feed data to algorithms so they learn patterns and
generalize to new situations.
Simple idea:
Traditional programming = Rules + Data → Output
Machine Learning = Data + Output → Learns rules (Model)
2) AI vs ML vs Deep Learning
AI: Broad field of making machines intelligent.
ML is a subset of AI that uses data to learn. Deep Learning (DL): Subset of ML using multi-
layer neural networks (useful for images, audio, text).
Analogy: AI is the full tree, ML is a big branch, DL is a branch on that branch.
3) Short History (Very Brief)
1956: Term “Artificial Intelligence” coined at the Dartmouth workshop.
No. of Roll: ____________ Course Description: Instructor: ____________
Department / University: ____________
Date: ____________
1. Acknowledgement
Artificial Intelligence (AI) is the science of making computers behave intelligently. Computers
can learn patterns from data and make predictions or decisions without being explicitly
programmed for each rule thanks to the machine learning (ML) subfield of artificial intelligence.
This assignment explains key concepts, types of ML, common algorithms, the ML workflow,
applications, challenges, and future directions, with small examples from online shopping and
hospital OPD management.
Table of Contents
Introduction
AI vs ML vs Deep Learning
A Brief History Key Concepts in ML
Machine Learning Types Common Algorithms (Plain Overview)
The ML Workflow (Step by Step)
Real-World Applications Mini Case Studies (E-commerce & OPD)
Tools & Libraries
Challenges, Risks & Ethics
Future Trends
Conclusion
Glossary
References
1) Introduction
Artificial Intelligence aims to build systems that can perceive, reason, and act. Voice
assistants, recommendation systems, and self-driving features are all examples. Machine
Learning is a way to achieve AI: we feed data to algorithms so they learn patterns and
generalize to new situations.
Simple idea:
Traditional programming = Rules + Data → Output
Machine Learning = Data + Output → Learns rules (Model)
2) AI vs ML vs Deep Learning
AI: Broad field of making machines intelligent.
ML is a subset of AI that uses data to learn. Deep Learning (DL): Subset of ML using multi-
layer neural networks (useful for images, audio, text).
Analogy: AI is the full tree, ML is a big branch, DL is a branch on that branch.
3) Short History (Very Brief)
1956: Term “Artificial Intelligence” coined at the Dartmouth workshop.
