Artificial Intelligence
A 20-episode university-level introduction to artificial intelligence and machine learning, taught by Jabril Ashe with John Green Bot. Covers core AI concepts, hands-on labs, and the social impact of AI.
Learn from: the original creator. Original content published on YouTube. DigitalSkillX organizes these public resources into a structured learning path. DigitalSkillX does not claim ownership or partnership.
Now playing: Robotics: Crash Course AI #11
This learning path follows the Crash Course Artificial Intelligence series in order. It starts with a preview and a definition of AI, then moves through supervised learning, neural networks, and training methods. Later episodes cover unsupervised learning, natural language processing, reinforcement learning, symbolic AI, robotics, and games. Four hands-on labs let you build AI systems for handwriting recognition, text generation, game playing, and movie recommendations. The final episodes cover recommender systems, web search, algorithmic bias, and the future of AI. The course is based on a university-level curriculum and is suitable for beginners who want a structured, practical introduction.
Beginners who want a structured free introduction before deeper practice.
Lesson 1: Crash Course Artificial Intelligence Preview
This preview introduces the Crash Course Artificial Intelligence series. Host Jabril Ashe explains that the series will trace the history of AI and show how it is used today. Co-host John Green Bot appears, and viewers learn they will build some AI systems themselves.
Open on YouTubeLesson 2: What Is Artificial Intelligence? Crash Course AI #1
This episode defines artificial intelligence and shows where it already appears in daily life, from autocomplete and video recommendations to photo recognition and self-driving cars. It sets up the rest of the course by explaining what AI is and what it is not.
Open on YouTubeLesson 3: Supervised Learning: Crash Course AI #2
Supervised learning is introduced as learning with training labels. The episode uses a donut versus bagel example to show how labeled data trains a model. It explains why supervised learning is the most widely used type of machine learning.
Open on YouTubeLesson 4: Neural Networks and Deep Learning: Crash Course AI #3
This episode combines artificial neurons into artificial neural networks. It explains why neural networks handle complicated tasks better than simpler methods and introduces deep learning. The focus is on how layers of neurons process information.
Open on YouTubeLesson 5: Training Neural Networks: Crash Course AI #4
Training neural networks is covered through backpropagation, the process of adjusting a network's math to reduce error. The episode explains how weights are optimized to find the best combinations. It uses a jungle analogy to show how training improves performance.
Open on YouTubeLesson 6: How to make an AI read your handwriting (LAB) : Crash Course Ai #5
In this first lab, viewers program a neural network to recognize handwritten letters. The goal is to convert part of John Green Bot's novel from handwriting to text. A Colab notebook is provided for following along.
Open on YouTubeLesson 7: Unsupervised Learning: Crash Course AI #6
Unsupervised learning is introduced as finding patterns without training labels. The episode contrasts it with supervised learning and focuses on one unsupervised technique. It explains when and why unsupervised learning is useful.
Open on YouTubeLesson 8: Natural Language Processing: Crash Course AI #7
Natural language processing is presented as a common way humans interact with computers. The episode covers how AI interprets language for search engines, smart assistants, and other tools. It builds on earlier image-focused examples by shifting to text.
Open on YouTubeLesson 9: Make an AI sound like a YouTuber (LAB): Crash Course AI #8
In this lab, viewers code a program that takes a one-word prompt and generates text in the style of John Green. The lab applies natural language processing to make John Green Bot sound more like the real John Green. A Colab notebook is provided.
Open on YouTubeLesson 10: Reinforcement Learning: Crash Course AI #9
Reinforcement learning is explained as training AI through rewards and penalties after it performs a task. The episode notes it is useful when we want AI to learn skills we do not fully understand ourselves. It contrasts this approach with earlier methods.
Open on YouTubeLesson 11: Symbolic AI: Crash Course AI #10
Symbolic AI, also called good old-fashioned AI, is introduced as an alternative to neural networks. It represents problems with symbols and uses logic to search for solutions. The episode explains how this approach differs from modern machine learning.
Open on YouTubeLesson 12: Robotics: Crash Course AI #11
This episode covers robotics and explains that robots are designed for specific tasks rather than general abilities. Examples include vacuuming, assembling cars, and exploring other planets. It discusses the gap between specialized robots and general household robots.
Open on YouTubeLesson 13: AI Playing Games: Crash Course AI #12
Games are presented as a useful test space for AI because they provide clear objectives and room for improvement. The episode reviews recent AI successes in games, from Jeopardy! to video games. It explains why games help researchers build better AI systems.
Open on YouTubeLesson 14: Let's make an AI that destroys video games: Crash Course AI #13
In this lab, viewers create a game called TrashBlaster and then build an AI to play it. The game is like Asteroids but set in the ocean with trash instead of asteroids. A Colab notebook is provided for following along.
Open on YouTubeLesson 15: Humans and AI working together: Crash Course AI #14
This episode focuses on the benefits of humans and AI working together as teams. It acknowledges concerns about automation and job loss but highlights how human-AI teams can combine strengths. The episode explains how each side fills in the other's weaknesses.
Open on YouTubeLesson 16: How YouTube knows what you should watch: Crash Course AI #15
Recommender systems are introduced as the backbone of online content discovery, from YouTube and Netflix to social media ads. The episode explains how these systems predict what users might want to see. It covers the basic ideas behind recommendation algorithms.
Open on YouTubeLesson 17: Let's make a movie recommendation system: Crash Course AI #16
In this lab, viewers build a movie recommendation system to help Jabril and John Green Bot find something they both can watch. The lab applies recommender system concepts to a practical problem. A Colab notebook is provided.
Open on YouTubeLesson 18: Web Search: Crash Course AI #17
This episode covers search engines as AI systems that help users find information. It explains how web crawlers, inverted indexes, and relevance measures work together. The focus is on the technology behind a list of search results.
Open on YouTubeLesson 19: Algorithmic Bias and Fairness: Crash Course AI #18
This episode examines five common types of algorithmic bias, including data that reflects existing biases and unbalanced training classes. It explains why bias matters and how it can affect AI decisions. The episode also discusses auditing datasets for these causes.
Open on YouTubeLesson 20: Cats vs Dogs? Let's make an AI to settle this: Crash Course AI #19
In the final lab, Jabril builds an AI to answer whether a cat or a dog makes people happier. While building it, he accidentally incorporates bias into the system. The lab shows how bias can enter an AI project even with good intentions.
Open on YouTubeLesson 21: The Future of Artificial Intelligence: Crash Course AI #20
The final episode looks toward the future of artificial intelligence. It explains why we do not yet have the artificial general intelligence seen in movies like Blade Runner, Her, or Ex Machina. It also discusses how current AI, such as Siri, falls short of AGI.
Open on YouTube0 of 21 lessons completed (0%).
Complete this learning path to become eligible for your DigitalSkillX certificate.
Cloud AI
AWS Certified Generative AI Developer Professional (AIP-C01) Free Learning Path
A free, hands-on path through Amazon Bedrock, RAG, vector stores, guardrails, and AI agents, built from Pratik Joshi's AIP-C01 course playlist.
Generative AI
Build 50+ Gen AI Projects from Scratch: A Hands-On Guide
A project-based path through generative AI. Build practical apps with open-source models, from text summarizers to multi-agent systems, and deploy them on Hugging Face Spaces.
Machine Learning
Machine Learning Crash Course: Core Concepts
A short video series from Google for Developers covering the fundamentals of machine learning, from gradient descent to neural networks and fairness.
Generative AI
Complete Generative AI Engineering Course
A hands-on path from beginner to advanced covering prompt engineering, RAG, agents, fine-tuning, and deployment with real projects.