Practice Artificial Intelligence in CS Thinking

Use these practice problems to test your method after reviewing the concept explanation and worked examples.

Quick Recap

Artificial intelligence is the field of building systems that perform tasks that normally require human-like perception, pattern detection, prediction, or decision making. Many AI systems learn patterns from large sets of data rather than following only hand-written rules.

AI systems learn patterns from examples so they can make useful predictions or decisions on new inputs.

Showing a random 20 of 50 problems.

Example 1

challenge
A team has only 200 labeled examples but millions of unlabeled ones. Describe an approach that uses both, and why pure supervised learning alone may struggle.

Example 2

medium
A recommendation model is retrained only on what users already clicked, so it keeps suggesting similar items and narrows over time. Name this dynamic.

Example 3

medium
You want to predict house prices from features (size, location) using past sales with known prices. Supervised or unsupervised, and why?

Example 4

medium
You have 1000 cat photos and 10 dog photos and train a classifier. Name the data problem and one concrete fix.

Example 5

easy
In y^=fฮธ(x)\hat{y} = f_\theta(x), what does xx represent?

Example 6

easy
Name one stakeholder group that should be considered when deploying an AI hiring tool.

Example 7

medium
A chatbot is fine-tuned to refuse to give medical advice. Is the safeguard primarily in the data, the model, or the deployment policy?

Example 8

hard
An AI tutor is more accurate for English speakers than Spanish speakers. Name two distinct fixes โ€” one at the data layer, one at the evaluation layer.

Example 9

challenge
A recommender shows users content similar to what they previously clicked. Over months, the diversity of recommendations narrows. Explain the feedback loop in terms of y^=fฮธ(x)\hat{y} = f_\theta(x) and propose two countermeasures.

Example 10

hard
Model A has precision 0.9, recall 0.5. Model B has precision 0.6, recall 0.85. For a tumor-screening tool where missing a tumor is far worse than a false alarm, which model is preferable and why?

Example 11

challenge
A school is choosing between AI-graded essays (fast, cheaper, opaque) and human-graded (slow, expensive, transparent). Frame the decision using stakeholders, benefits, harms, data use, and safeguards.

Example 12

easy
In y^=fฮธ(x)\hat{y} = f_\theta(x), what does y^\hat{y} stand for?

Example 13

easy
A model groups customers into clusters with NO labels provided. What type of learning is this?

Example 14

easy
A face-recognition system works poorly on groups underrepresented in its training data. What is the root cause?

Example 15

medium
A spam classifier flags 90 of 100 real spam emails (and misses 10). What is its recall on spam?

Example 16

medium
Why is a held-out test set kept SEPARATE from the training set?

Example 17

easy
True or false: An AI trained only on adult speech will usually understand kids' voices just as well.

Example 18

challenge
A model has 95% training accuracy but 70% test accuracy. A second model has 80% training and 78% test. Which is likely better for real use, and what does the gap indicate?

Example 19

easy
What is the name for the process of measuring how well a trained model performs on unseen data?

Example 20

medium
Why should an AI grading system keep a sample of work reviewed by humans, even after deployment?