What is Artificial Intelligence?
Artificial Intelligence (AI) refers to computer systems designed
to perform tasks that typically require human intelligence.
These tasks include problem-solving, decision-making,
learning from experience, understanding language, and
recognizing patterns.
Think of AI as a way to make computers "think" and "act" like
humans to some extent.
Examples of AI in Daily Life
Voice Assistants
Recommendation Systems
Chatbots
Self-driving Cars
Spam Filters
Fraud Detection
Medical Diagnoses
Many More!
History 🕰 1950 – Turing Test :
of AI Alan Turing proposed a test to see if machines can think like humans?
🧠 1956 – AI is Born :
John McCarthy coined the term Artificial Intelligence at the Dartmouth Conference.
♟ 1997 – AI Beats a Chess Champion
IBM’s Deep Blue defeated world champion Garry Kasparov.
🧠 2011 – Watson Wins Jeopardy!
IBM Watson defeated human champions in a quiz show using natural language processing.
2016 – AlphaGo Beats a Go Champion
Google’s AlphaGo defeated Lee Sedol, mastering a game considered too complex for AI.
2020s – AI Creates & Communicates
AI models like ChatGPT and DALL·E generate text, images, and even code.
Future – Towards AGI?
AI is advancing rapidly, with discussions on Artificial General Intelligence (AGI).
Types of AI
1️⃣ Narrow AI (Weak AI)
This is the AI we use today. It is designed to do one specific task, like recognizing faces, recommending
movies, or answering questions. It cannot think or learn beyond what it is programmed for. Examples
include Siri, Alexa, Google Search, and self-driving cars.
2️⃣ General AI (Strong AI)
This is AI that can think, learn, and solve problems just like a human. It would understand different tasks
and apply knowledge across various situations. However, this type of AI does not exist yet and is still being
researched.
3️⃣ Super AI
This is a future concept where AI would be more intelligent than humans in every way. It could think
independently, be creative, and even have emotions. Some scientists believe it may be possible, while others
worry about its risks.
Why AI Now?
AI has been around for decades, but it is advancing
rapidly today because of three key factors:
1️⃣ More Data 📊
•The internet, smartphones, and sensors generate massive amounts of data every second.
•AI needs data to learn and improve, and now we have more than ever before!
2️⃣ More Computing Power 💻
•Faster and cheaper processors (like GPUs and TPUs) allow AI to process huge datasets quickly.
•Cloud computing makes AI accessible to everyone, not just big tech companies.
3️⃣ Better Algorithms 🧠
•Advances in Machine Learning (ML) and Deep Learning allow AI to make smarter decisions.
•AI models like ChatGPT and self-driving cars are possible because of these improvements.
Artificial Intelligence techniques
Artificial Intelligence can be used to solve real-world problems by implementing the following
processes/ techniques:
What is Machine Learning?
Machine Learning (ML) is a type of AI that allows computers to learn from data and
improve their performance without being explicitly programmed. Instead of following
fixed rules, the machine finds patterns in data and makes decisions based on them.
Examples
✅ Spam Filters – Email services like Gmail use ML to detect spam
emails based on patterns in text, sender info, and past user behavior.
✅ Image Recognition – Facebook and Google Photos use ML to
recognize people in pictures.
✅ Movie & Shopping Recommendations – Netflix and Amazon
suggest shows or products based on your past activity.
Why Machine Learning?
• Let’s say we want to design a spam filtering system
• One approach is to use traditional programming techniques
• Look for words or phrases such as: credit card, free, bank information
• Write a detection algorithm for each of the patterns
• Test your program and improve it
Why Machine Learning?
• A spam filter based on machine learning automatically learns which words and phrases are
good predictors
• Possible benefits: simpler, easier to maintain, and more accurate
• The examples that the system uses are called the training set
• We should also think of a performance measure
Types of machine learning
ML systems can be classified according to the amount and type of supervision
1. Supervised learning
The model learns from labeled data (data with correct answers).It makes predictions
based on patterns in past data.
Examples:
✅ Spam detection – AI learns from labeled emails ("spam" or "not spam").
✅ House price prediction – AI learns from past sales data to predict future prices.
Classification
Regression
Types of machine learning
2️⃣ Unsupervised Learning
The model learns from unlabeled data (no correct answers given). It finds patterns,
relationships, or groups in the data on its own.
Examples:
✅ Customer segmentation – AI groups similar customers based on shopping habits.
✅ Anomaly detection – AI detects fraud in bank transactions.
Types of machine learning
3️⃣ Reinforcement Learning 🎮 (Learning by Trial and Error)
The model learns from experience by interacting with an
environment and receiving rewards or penalties. It improves
by maximizing rewards over time.
Examples:
✅ Self-driving cars – AI learns to drive safely by making decisions and getting feedback.
✅ AlphaGo – AI learned to play and beat humans in the game of Go.
