StudyBrixFree worksheets, study guides and courses

Artificial intelligence · Grades 9–12

AI, machine learning and useful problem definitions

Artificial intelligence is a broad field of methods for tasks involving perception, prediction, planning or language. Machine learning fits patterns from data rather than requiring every rule to be handwritten.

Make a worksheet

Prerequisites

Basic computing and reading simple tables.

Study notes

AI and learning

Artificial intelligence is a broad field of methods for tasks involving perception, prediction, planning or language. Machine learning fits patterns from data rather than requiring every rule to be handwritten.

Task definition

Specify the input, desired output, users and consequences of errors before choosing a model. A clear baseline can reveal whether machine learning is necessary.

Prediction versus decision

A score or prediction does not decide what action is acceptable. Human policy, constraints and domain knowledge still matter.

Limits

Fluent or confident output is not proof of correctness. These lessons teach concepts with small examples, not claims that a model understands everything.

Worked examples

Which best describes a supervised-learning task?

Supervised learning uses target-labelled training examples.

Learn a mapping from examples with target labels

What should normally come before choosing a model architecture?

Task definition determines evaluation and practical constraints.

Define the task and error costs

Check your understanding

  1. Which is a regression target?

    1. A file extension only
    2. A numeric delivery-time estimate
    3. A yes/no label only
    4. A colour category only

  2. Which is a classification target?

    1. A temperature reading only
    2. A continuous length only
    3. An item category
    4. A decimal weight only

  3. A rule baseline solves 72 of 100 toy examples correctly. Find its accuracy as a percentage.

  4. Why should a simple baseline be measured before developing a complex model?

Answers and marking guidance

Answers and marking notes
  1. A numeric delivery-time estimate

    Regression predicts a numerical quantity.

  2. An item category

    Classification predicts a class or category.

  3. 72 %

    72/100×100=72%.

  4. It establishes a reference for improvement, cost and failure modes. A complex model is not useful merely because it is complex.

    Credit measurable comparison and practical value.

Further reading and review references

These are reference links, not copied exercises, institutional endorsement or proof of independent review.

AI-assisted preview; independent educational review required. Level labels describe prerequisites, not accreditation or official curriculum alignment.