Skip to content
Back to How Models Learn
WT

What Training Actually Changes

Training does not rewrite reality or magically create understanding. It changes the model's internal parameters so predictions improve over repeated examples.

35 minHow Models Learneasy100 XP

Listen to hear this room section by section.

Key Ideas

Work through these sections in order. Each one builds the mental model you need before the checkpoint questions will feel easy.

When a model is trained, the dataset provides examples and answers, but the rows of the dataset are not what get updated over and over. The dataset acts as the teaching material. The thing that changes is the model's internal parameter values, often called weights.

This distinction sounds technical, but it is the key to understanding learning. If a learner thinks the model improves by storing the raw data directly, it becomes harder to understand generalization, overfitting, and evaluation later on. Training is about adjusting internal settings so the model behaves differently on inputs, not about rewriting the facts in the table.

In a simple supervised setup, the model sees an example, produces a prediction, compares that prediction to the known target, and then updates its parameters so similar mistakes are less likely in the future. The data stays the same. The model changes.

That is why people talk about fitting a model to data. The data is the reference point. The model is the flexible object being nudged and shaped in response to what the data shows.

You've opened 1 of 4 sections. Once the ideas feel clear, move into the checkpoint block below.

Check Your Understanding

These checkpoints reinforce the lesson you just read. If one feels fuzzy, reopen the relevant section above before trying again.

3 checkpoints
1

Task 1

Name what training changes

Choose the answer that best describes what gets updated during training.

What usually changes when a model is trained on examples?

2

Task 2

Rebuild the training loop

Put the main steps of the training story in the right order.

Order the high-level training loop from start to finish.

1

The model receives an example

2

The model makes a prediction

3

The prediction is compared with the target

4

The parameters are adjusted

3

Task 3

Explain why this is not memorization

Write a short explanation of why training is more than storing the dataset.

Why is training not the same as simply storing every answer from the dataset?

Ready To Move On?

Up next: Module 1 Checkpoint: Read a Learning Problem