1. Foundations6 lessons
  2. Inside the Model5 lessons
  3. How Learning Works5 lessons

Topic 1 of 3

Foundations

The concepts everything else builds on — you'll sort out what separates a program from a model and what's behind probabilities, vectors, and hardware.

6 of 6 lessons readableStart

What this topic covers

This topic establishes the shared vocabulary for everything that follows. Its lessons begin with familiar computer programs and lead step by step toward the numerical structures, probabilities, and technical foundations of modern AI models.

You can read every lesson on its own. The displayed order is still deliberate: new terms build on ideas already explained, without turning the knowledge base into a rigid course.

Topic 1 of 3

Lessons in this topic

Every lesson stands on its own. In this order, the ideas connect especially clearly.

  1. Program, Algorithm, Model Compared

    Telling program, algorithm and AI model apart: why a model is not made of written-down rules but of numbers that are set during training.

    Read≈ 13 min

  2. Input and Output: How a Function "Thinks"

    What does an AI model receive, and what does it give back? From the spam filter to image recognition to the chatbot: why the output is usually a list of ratings, and how an answer is built from it piece by piece.

    Read≈ 11 min

  3. How Language Becomes Numbers: Tokenizer, IDs, Vocabulary

    Shows how a tokenizer splits text into reusable pieces, numbers them through a fixed vocabulary, and turns them into the numerical input of a language model.

    Read≈ 16 min

  4. Scalar, Vector, Matrix, Tensor: The Building Blocks of the Numbers

    From the weather app to the chatbot: how a number, a list, a table, and a stack of tables relate to each other, and why your chat message and your photo are exactly such blocks of numbers for a model.

    Read≈ 14 min

  5. Probability and Softmax: How a Model Decides

    How a language model turns its scores into percentages, why it sometimes picks the obvious choice and sometimes something else, and what temperature has to do with it.

    Read≈ 15 min

  6. Parameters, Training vs. Inference, Hardware: How a Model Runs

    What is inside a finished AI model, what people decide before training, why learning costs so much more than using, and what hardware a model needs.

    Read≈ 14 min

Look it up

Terms from this topic

Short explanations of the technical terms used by the lessons already available.