AI & ML Orientation

Starting diagnostic

Find your strongest entry point.

This is a baseline, not a gate. It does not mark lessons complete, and the recommendation changes where you begin rather than what you are allowed to learn.

1. For a feature matrix with 20 rows and 3 columns, what does one row usually represent?

One feature with twenty models.The learning rate.A probability distribution only.One example with three features.

2. Why is test data kept separate during model selection?

To make training loss smaller.Because test data cannot have labels.To avoid writing Python.To estimate the selected workflow without adapting choices to those examples.

3. What is the derivative of (w - 2)^2 with respect to w?

2(w - 2)2w^2w - 2

4. A classifier finds 8 of 10 actual positives. What is its recall?

0.28.0Cannot be measured from those counts.0.8

5. What does X.mean(axis=0) usually compute for rows-as-examples data?

One mean per feature.A model prediction.One mean per example.A train/test split.

Learn by doing

Explore the concept.

Make a prediction before changing a control. Run the experiment, explain what moved, and compare the result with the theory below.

Initializing Interactive Playground...

Complete lesson

Detailed concept deep dive.

Build intuition first, then work through implementation, mathematical derivations, failure analysis, and real system decisions.

7 guided chapters

IntuitionCorePractice

A clear map prevents beginners from treating every AI term as interchangeable or learning advanced tools before they can evaluate a simple model.

Before working through the formal derivations, connect the vocabulary to one small, concrete example. The goal is not to memorize definitions in isolation. It is to understand what each idea represents, which assumptions make it valid, and how the pieces relate to one another.

Ideas to understand

Rules versus learned patterns
Features, labels, models, training, inference, and evaluation
Regression, classification, clustering, generation, and decision systems

Learn by doing

Make the idea concrete

Explain AI and ML orientation with a concrete example and no unexplained jargon.

Try this

Define “Rules versus learned patterns” in your own words, then annotate one concrete AI & ML Orientation input and output.
Construct one valid case and one counterexample for “Features, labels, models, training, inference, and evaluation”; explain which assumption separates them.
Predict how “Regression, classification, clustering, generation, and decision systems” will change one visible playground result, then test and record the before/after values.

Evidence of understanding

You can explain the example without relying on jargon.
You can name the assumptions and identify what would invalidate them.
You can connect the example to at least one real ML use case.

Reflection note

What part of the AI & ML Orientation mental model still feels least intuitive, and what example would help clarify it?

Saved in your browser progress and included in exports.

Practice with code

Make the idea executable.

Complete the starter code, use progressive hints, and pass deterministic checks in the browser.

Runnable Python lab

Compare a rule with observed labels

Complete a tiny threshold classifier and compute its accuracy. The point is to establish a transparent baseline before considering a learned model.

Test output

Run the code when you are ready. The first load downloads the in-browser Python runtime.

Code runs only in a time-limited browser worker. It is not sent to the IntuitiveAI server. Do not paste secrets.

Expected result

predictions: [0, 0, 0, 1, 1, 1]
accuracy: 1.0
ALL TESTS PASSED

Keep learning

Papers, standards, and practical references.

Start with the free primary sources. Books are included where a longer, connected treatment is worth the investment.

The Python Tutorial

The official, free introduction to Python syntax and core programming ideas.

DocumentationFree

Google Machine Learning Glossary

A free glossary for core ML terminology and common model concepts.

DocumentationFree

What this lesson will help you understand.

Find your strongest entry point.

Explore the concept.

Detailed concept deep dive.

The mental model and essential vocabulary

Make the idea concrete

Limits, failure modes, and diagnosis

From the idea to a working experiment

Production decisions and capstone challenge

A useful map of AI and machine learning

Turn a product question into a learning problem

What credible ML evidence looks like