Introduction to AI: Course Overview

About Introduction to AI

Artificial intelligence is the practice of building systems that can learn patterns from data and make predictions or decisions, rather than following rules written by hand. This course starts with What Is AI? — the history, key terms, and how AI, machine learning, and deep learning relate — then the Math Foundations (linear algebra, probability, and calculus) that everything else builds on.

From there you'll work with real data: cleaning, transforming, and preparing it under Data & Preprocessing, before training your first models with Supervised Learning (regression and classification) and Unsupervised Learning (clustering and dimensionality reduction).

The course then moves into Neural Networks and Deep Learning, the architectures behind modern AI, and applies them to two major domains: Natural Language Processing for working with text, and Computer Vision for working with images. You'll also explore Generative AI & LLMs, the technology behind tools like ChatGPT and image generators.

Finally, you'll learn how to judge whether a model is actually good with Model Evaluation, and how to build and deploy AI responsibly with AI Ethics & Bias.

No prior AI experience is required, but basic comfort with Python and simple math will help. This course walks through the field in order, so each module builds directly on the last.

Content

12 modules

What Is AI?

A tour of the field: how AI, machine learning, and deep learning relate, a short history, and where AI shows up in everyday products.

AI Basics History of AI Terminology

Math Foundations

Just enough linear algebra, probability, and calculus to understand how models learn — vectors, matrices, distributions, and gradients.

Linear Algebra Probability Calculus

Data & Preprocessing

Cleaning messy data, handling missing values, feature scaling, and splitting datasets so models learn — and are tested — fairly.

Data Cleaning Feature Engineering Pandas

Supervised Learning

Training models on labeled data with regression and classification: linear models, decision trees, and nearest neighbors.

Regression Classification Scikit-learn

Unsupervised Learning

Finding structure in unlabeled data with clustering methods like k-means, and reducing dimensions with PCA.

Clustering K-Means PCA

Neural Networks

Perceptrons, layers, activation functions, and backpropagation: how a network actually learns from data.

Neural Networks Backpropagation Activation Functions

Deep Learning

Going deeper with multi-layer networks, regularization, and optimization using frameworks like PyTorch or TensorFlow.

Deep Learning PyTorch TensorFlow

Natural Language Processing

Turning text into features, word embeddings, and the transformer architecture behind modern language models.

NLP Embeddings Transformers

Computer Vision

How machines interpret images: convolutional neural networks, image classification, and object detection basics.

Computer Vision CNNs Image Classification

Generative AI & LLMs

How large language models and image generators work, prompting techniques, and where generative AI is headed.

LLMs Generative AI Prompting

Model Evaluation

Accuracy, precision, recall, and other metrics for judging whether a model actually works — and avoiding overfitting.

Metrics Overfitting Cross-Validation

AI Ethics & Bias

Recognizing bias in data and models, and the responsible-AI practices needed before shipping to real users.

AI Ethics Bias Responsible AI

What You Can Do After This Course

By the end of the curriculum you'll have shipped five real projects and covered the full path from raw data to a trained AI model. Concretely, you'll be able to:

Explain how AI systems learn — the difference between AI, machine learning, and deep learning, and the math underneath them.

Prepare real datasets — clean, transform, and split data so models can learn from it fairly.

Train supervised and unsupervised models — regression, classification, clustering, and dimensionality reduction.

Build and train neural networks — from a single perceptron up to deep networks in PyTorch or TensorFlow.

Apply AI to text and images — NLP with transformers and computer vision with CNNs.

Work with generative AI — understand how LLMs and image generators work, and how to prompt them effectively.

Evaluate and ship responsibly — measure model quality, spot bias, and apply responsible-AI practices before deployment.

Show proof of skill — an ML fundamentals project, a from-scratch digit recognizer, a CNN image classifier, a sentiment analysis model, and an LLM-powered chatbot.

Introduction to AI