🟢 Session 2 — Quiz: How does AI learn?

Applied AI — Yann Isola · Beginner Level 10 questions · Only 1 correct answer per question · Answer key commented at the end of the document. Facilitator tip: in groups, “show of hands” or teams mode — it’s more fun.

Question 1 — In supervised learning, what do we give the AI so that it learns?

HAS Rules written by hand by programmers B Examples accompanied by the correct answers (labels) C Examples without any indication D Rewards and punishments

Question 2 — “Sorting a bag of candy by color without anyone telling you the categories” is the analogy of…

HAS Supervised learning B Reinforcement learning C Unsupervised learning D Overfitting

Question 3 — An AI plays millions of rounds of a game, gaining points when it succeeds, losing points when it fails, and improving. It is…

HAS Supervised learning B Unsupervised learning C Reinforcement learning D From cheating

Question 4 — Why do we say that data is the “fuel” of AI?

HAS Because servers consume gasoline B Because without data, an AI cannot learn anything: all its knowledge comes from its examples C Because data costs the same as oil D Because AI burns data after reading it

Question 5 — Your AI should recognize dogs, but you ONLY trained it with photos of Labradors. What might happen to a Chihuahua?

HAS Nothing, a dog is a dog B She will recognize him even better, because he is smaller C She risks not recognizing it: her data lacked diversity D She will refuse to answer out of caution

Question 6 — What is the difference between training and using (inference) an AI?

HAS None, it's the same process B Training is long and expensive (the AI learns); use is quick (the AI applies what it knows) C Use is longer than training D Training is done after use

Question 7 — An artificial neuron is above all…

HAS An exact copy of a neuron in the human brain B A living electronic chip C A small calculator that receives signals, gives them more or less importance (weight), and sends a signal in turn D A program that stores memories

Question 8 — In a neural network, “learning” essentially means…

HAS Add new neurons to each correct answer B Gradually adjust the weights (the importance of the connections) to reduce errors C Copy data into a large memory D Increase CPU speed

Question 9 — An AI obtains 99.9% success on its training examples, but only 60% on new examples. Diagnosis?

HAS It’s excellent AI: 99.9%, it’s almost perfect! B This is overfitting: she “learned by heart” instead of understanding C It's normal, AI is always bad on new things D New examples are necessarily false

Question 10 — Why do we keep test data that the AI NEVER sees during training?

HAS To save memory B Because it is a legal obligation C To check that she knows how to generalize about something never seen before, like a test with new exercises D Because this data is of lower quality