AI Fundamentals

Welcome to the AI Fundamentals tutorials.

This tutorial is designed to build a strong foundation in Artificial Intelligence, starting with the basic concepts and gradually moving toward modern AI systems.

You will first learn what Artificial Intelligence means and how Machine Learning enables computers to learn patterns from data. You will then explore Neural Networks, Deep Learning, and Transformers to understand the foundations behind today’s AI systems.

From there, you will learn the fundamentals of Large Language Models, including tokens, tokenization, parameters, context windows, inference, temperature, hallucinations, model knowledge, and prompting.

The final tutorials introduce how these AI fundamentals are applied when building AI applications.

The goal is to help you understand the concepts behind modern AI systems, rather than simply learning AI terminology.

📋 What You Will Learn

• What Artificial Intelligence is and how it differs from traditional software.
• How Machine Learning works, including its different types and how models learn patterns from data.
• What Neural Networks and Deep Learning are and how they work.
• How Transformers and attention enable modern AI systems.
• What Large Language Models are and how they learn and generate text.
• How LLMs work with tokens, parameters, context windows, and inference.
• How generation settings such as temperature affect LLM responses.
• Why LLMs hallucinate and what model knowledge and knowledge cutoffs mean.
• How prompting works and how to improve prompts.
• How AI models are used to build applications, including application architecture and cloud vs. local models.
• How to build a basic LLM application.

🧭 Tutorials

AI Foundations

1. Introduction to AI
2. AI Common Generative AI Terms
3. What is Machine Learning?
4. Types of Machine Learning
5. What is a Neural Network?
6. What is Deep Learning?
7. AI Transformers and Attention

Large Language Models

1. Large Language Models (LLMs)
2. LLM Tokens and Tokenization
3. How LLMs Learn
4. LLM Parameters
5. LLM Context Windows
6. LLM Inference and Generation Settings
7. LLM Temperature
8. LLM Hallucinations
9. LLM Model Knowledge and Knowledge Cutoff
10. LLM Prompting Basics
11. LLM Prompt Improvement Loop

Building AI Applications

1. AI LLMs vs Traditional Software
2. AI Application Architecture
3. AI Models vs AI Applications
4. AI Cloud vs Local Models
5. AI Build Your First LLM Application

🚀 Getting Started

If you are new to AI, start with Introduction to AI.

The tutorials are arranged to gradually build your understanding, starting with the foundations of AI and Machine Learning, moving through Neural Networks, Deep Learning, Transformers, and LLMs, and finally showing how these concepts are used in AI applications.