01. Introduction to AI

AI is the ability of a machine to perform tasks that would normally require human intelligence.

AI systems can:

• Understand language (read, write, translate)
• Recognize patterns (faces, objects, speech)
• Make decisions (recommend, diagnose, classify)
• Learn from experience (improve over time with data)

The word “artificial” = made by humans. The word “intelligence” = ability to learn, reason, and solve problems.

Traditional programs follow explicit rules:

if temperature > 37.5 → print "fever"

AI programs learn rules from data:

data: [thousands of patient records]
model learns: what patterns predict fever

Instead of a programmer writing every rule, the machine figures out the rules itself.

flowchart LR
    subgraph Traditional["Traditional Programming"]
        direction TB
        R[Rules] --> C1[Computer]
        D1[Data] --> C1
        C1 --> O1[Output]
    end
    subgraph ML["AI / Machine Learning"]
        direction TB
        D2[Data] --> C2[Computer]
        O2[Expected Output] --> C2
        C2 --> R2[Learned Model]
    end
    style Traditional fill:#1e1b4b,stroke:#7c3aed,color:#e2e8f0
    style ML fill:#14532d,stroke:#059669,color:#e2e8f0

• Not magic — it’s math + data + compute
• Not “thinking” the way humans do
• Not always right — it makes mistakes
• Not one thing — it’s a broad field with many subfields

Narrow AI (what exists today): Excellent at ONE specific task.

• GPT-4 writes text but can’t drive a car
• AlphaGo beats humans at Go but can’t cook

General AI (hypothetical): Can handle any task a human can.

• Does not exist yet

Q: What is Artificial Intelligence?

A: AI is the simulation of human intelligence in machines — enabling them to perform tasks like understanding language, recognizing patterns, making decisions, and learning from data without being explicitly programmed for every scenario.

Q: What is the difference between traditional programming and AI?

A: In traditional programming, a developer writes explicit rules: if X then Y. In AI, the system learns rules from data — you feed it examples, and it figures out the patterns. The developer designs the learning process, not every individual rule.