Lesson 1.5 · Beginner

How models learn from examples

Understand parameters, loss, and why a good training score is not enough.

3 min read

The short version

A model learns by guessing, being told how wrong it was, and adjusting, over millions of examples. After that it is fixed. Showing it your document in a chat does not teach it anything permanent, and knowing how it learned explains why it can be good at patterns and poor at exact facts.

On this page +

The idea What to check Try it

The idea

A neural network is a model made of linked layers of maths. Training adjusts its stored numbers. The system tries a task, measures an error, and uses that feedback to adjust those numbers. Repeating this process helps it learn patterns.

What to check

Training is different from reading a file in a chat. A file can affect the next answer without changing the model's stored numbers. The app may also save files or memories. Check its terms and settings; do not assume the file vanishes when the chat ends.

A model can do well on examples it has seen and poorly on new ones. A useful test uses fresh examples that did not guide the setup.

Try it

You tune a prompt after each of thirty test questions. It now gets them all right. Does that prove it will get new questions right?

Check your understanding

No. You have shaped the prompt around that set. Test it on a fresh set and record the errors as well as the successes.

Examples are teaching material. For legal rules, read the current primary text linked below. A revision date does not certify every claim.

Sources and further reading

Linked sources support the technical background identified below. The legal workflows, prompts, and fictional examples are original editorial exercises; they are not claims of endorsement by the linked authors.

CoursePyTorch · Optimizing model parameters

Loss, gradients, and optimization in a training loop.

← Back to chapter