What is AI for Everyone?
Hello. I'm Lee Jong-hyeon, an AI researcher. I majored in computer science and am currently in the Master's program in AI at Yonsei University, researching machine learning and deep learning.
I have participated in various AI competitions and developed models used in industry. Through that, I learned one important lesson: while technique matters, what really determines the difference in performance is understanding the fundamentals. These days you can implement models quickly with vibe coding, but when performance doesn't meet expectations, analyzing the cause and improving is still not easy. Without an understanding of the mathematical foundations and AI principles, it's difficult to structurally identify where bottlenecks occur.
So I developed and released this learning platform based on what I've studied and organized. If you'd like lectures or training, feel free to reach out at rivolt2022@gmail.com and I'll be glad to help.
Curriculum
The platform is structured as a step-by-step curriculum from basic math to core deep learning concepts.
📘 Part 1. Basic Math and AI
- Ch.00 Basic Math and AI: Learning the Language of AI
- Ch.01 Functions: AI's Basic Unit of Input and Output
- Ch.02 Exponents and Exponential Functions: The Math of Growth and Activation
- Ch.03 Logarithm: Turning Multiplication into Addition, Designing Loss
- Ch.04 Limits and ε-δ: Defining 'Approaching Infinitely Close'
- Ch.05 Continuity: Smooth Curves, Opening the Door to Calculus
- Ch.06 Derivatives: Instantaneous Slope, the Compass of Learning
- Ch.07 Chain Rule: Unraveling Nested Functions, the Core of Backpropagation
- Ch.08 Partial Derivatives and Gradient: Multi-Variable World, Direction of Gradient Descent
- Ch.09 Integration: Area and Accumulation, the Bridge to Probability
- Ch.10 Random Variables and Distributions: Capturing Uncertainty in Numbers
- Ch.11 Mean and Variance: Center and Spread of Distributions
- Ch.12 Uniform and Normal Distributions: From Initialization to Prediction
📗 Part 2. Understanding Deep Learning Structure
- Ch.00 First Steps in Deep Learning: How Does AI Think?
- Ch.01 Dot Product: Finding Similarity in Data
- Ch.02 Matrix Multiplication: The Magic of Batch Computation
- Ch.03 Linear Layer: Weights That Decide Importance
- Ch.04 Activation Functions: Adding Judgment to AI
- Ch.05 Artificial Neuron: The Unit That Gathers Information and Sends Signals
- Ch.06 Batch Processing: Learning in Batches
- Ch.07 Weight Connections: The Chains That Build Intelligence
- Ch.08 Hidden Layers: The Invisible Depth of Thought
- Ch.09 Deep Neural Networks: The Power to Solve More Complex Problems
- Ch.10 Width and Neurons: Finding More Features at Once
- Ch.11 Softmax: Turning Results into Confidence
- Ch.12 Gradient and Backpropagation: Learning from Mistakes
- Ch.13 Summary: A Map of AI at a Glance
Rather than simple concept summaries, the content follows the flow of computation step by step so you understand 'why it works this way.' It's visualization- and interaction-focused.
Learning Approach
Rather than listing concept summaries, the content follows the flow of computation step by step so you understand 'why it works this way.' It's centered on visualization and interaction, with immediate AI coach feedback to correct misconceptions.
Future Plans
We plan to continuously expand with more AI education content, including machine learning. If you're interested, feel free to contact us at rivolt2022@gmail.com anytime.
Add to Chrome Web Store
Install the Chrome extension to open the learning page in a new tab.
Add to Chrome Web StoreIt's still an early version, but we're improving it continuously. Your feedback is welcome and will be actively incorporated.