What is Artificial Intelligence?

Artificial Intelligence (AI) is the broad field of creating machines that can perform tasks that typically require human intelligence. Let's break down the hierarchy:

AI (Artificial Intelligence) — The broadest term. Any technique that enables machines to mimic human behavior.

ML (Machine Learning) — A subset of AI. Systems that learn from data instead of being explicitly programmed.

DL (Deep Learning) — A subset of ML. Uses neural networks with many layers to learn complex patterns.

Generative AI — A subset of DL. Models that can generate new content (text, images, code).

The AI Hierarchy

AI ⊃ Machine Learning ⊃ Deep Learning ⊃ Generative AI Each is a subset of the one before it. Not all AI is ML, and not all ML is deep learning.

Types of Machine Learning

Supervised Learning

You provide labeled data (inputs + correct outputs). The model learns the mapping.

Classification: Predict a category (spam/not spam, cat/dog)

Regression: Predict a number (house price, temperature)

Unsupervised Learning

You provide unlabeled data. The model finds hidden patterns.

Clustering: Group similar items (customer segments)

Dimensionality Reduction: Compress data while preserving structure

Reinforcement Learning

An agent learns by taking actions in an environment and receiving rewards.

Game playing (AlphaGo)

Robotics

RLHF for LLMs

Key Terminology

Term	Definition
Model	A mathematical function that maps inputs to outputs
Training	The process of adjusting model parameters using data
Inference	Using a trained model to make predictions
Features	Input variables the model uses to make predictions
Labels	The correct answers (in supervised learning)
Epoch	One complete pass through the training data
Batch	A subset of training data processed at once
Loss	A measure of how wrong the model's predictions are
Optimizer	Algorithm that adjusts parameters to minimize loss