AI Basics

Practice questions

A student uses a chatbot to prepare notes on exam dates and fees. What is the right practice?

  1. Copy the chatbot's answer because it sounds confident
  2. Ask the same chatbot again until it gives the same answer twice
  3. Use the answer only if it is long
  4. Check each date and fee against the official notice before relying on it
Answer and explanation

Answer: D

Chatbots can hallucinate, and repetition or confident tone does not make an answer true. Facts such as dates and fees must be checked against the official source.

A spam filter lets 12 scam emails into the inbox and moves 3 genuine emails to spam. How many false negatives and false positives are there?

  1. 3 false negatives and 12 false positives
  2. 15 false positives and no false negatives
  3. 12 false negatives and 3 false positives
  4. 12 false negatives and no false positives
Answer and explanation

Answer: C

Scams let through are cases where the filter said 'not spam' wrongly: 12 false negatives. Genuine emails marked spam are 'spam' said wrongly: 3 false positives.

Why can a chatbot state a wrong fact in a confident tone?

  1. It produces likely-sounding words from patterns rather than looking facts up in a checked record
  2. It deliberately lies to users
  3. Its screen is faulty
  4. It has general intelligence and disagrees
Answer and explanation

Answer: A

A language-model chatbot generates the most likely next words. It aims to sound right, not to verify facts, so a weak pattern can still produce fluent, false output - hallucination.

A factory arm repeats the same welding movement all day with no sensing or decision. It is best described as:

  1. Computer vision
  2. Automation, not AI
  3. Deep learning
  4. General AI
Answer and explanation

Answer: B

A machine repeating a fixed motion follows a set program. It becomes AI only when it senses its surroundings and makes decisions, as a robot finding its way around obstacles does.

An online shop groups its customers into types by their buying habits, with no labels given in advance. This is:

  1. Supervised learning
  2. Reinforcement learning
  3. An expert system
  4. Unsupervised learning
Answer and explanation

Answer: D

Finding groups in unlabelled data is unsupervised learning. Supervised learning needs labelled examples, and reinforcement learning uses rewards and penalties.

A smart speaker hears a spoken question, works out its meaning and replies aloud. Which sequence of branches is used?

  1. Computer vision → robotics → NLP
  2. NLP → speech recognition → computer vision
  3. Speech recognition → NLP → speech synthesis
  4. Expert system → computer vision → robotics
Answer and explanation

Answer: C

Voice is turned into text by speech recognition, the meaning is worked out by NLP, and the reply is spoken by speech synthesis (text-to-speech). No images or physical movement are involved.

A rules-based system has one advantage over most learning systems. Which?

  1. Its decisions are easy to explain because the rules can be read
  2. It needs huge datasets
  3. It handles messy, varied input better
  4. It improves automatically with more data
Answer and explanation

Answer: A

In a rules-based system you can point to the rule that caused a decision. Learning systems handle varied input and improve with data, but their decisions are often hard to explain.

Which activity is inference, not training?

  1. Adjusting a model's weights using thousands of labelled photos
  2. A phone unlocking when its owner looks at it
  3. Labelling mango photos as ripe or unripe
  4. Collecting a dataset of voice recordings
Answer and explanation

Answer: B

Unlocking a phone uses the already trained face model on a new input - that is inference. Adjusting weights is training, and labelling and collecting data are preparation for training.

A company uses the same learning algorithm on two different datasets - one of Hindi emails, one of English emails. What results?

  1. One model shared by both
  2. No model, because the algorithm is the model
  3. The datasets merge automatically
  4. Two different models, because a model depends on the data it was trained on
Answer and explanation

Answer: D

The algorithm is the learning method; the model is what that method produces from particular data. Different data give different models.

Why did expert systems prove brittle?

  1. Every rule had to be written and updated by hand, and they failed on cases their rules did not cover
  2. They needed millions of labelled photographs
  3. They could only run on smartphones
  4. They learned too quickly from data
Answer and explanation

Answer: A

Expert systems hold human-written if-then rules. Writing and maintaining those rules was slow and costly, and a case outside the rules left the system stuck.

How many years separate Alan Turing's 1950 paper from Deep Blue's 1997 win over Kasparov?

  1. 41
  2. 46
  3. 47
  4. 6
Answer and explanation

Answer: C

1997 − 1950 = 47 years. (Dartmouth 1956 to Deep Blue 1997 is 41 years, and Turing's paper to Dartmouth is 6 years.)

Arrange in time order: (1) Deep Blue beats Kasparov, (2) the term 'artificial intelligence' is coined for the Dartmouth workshop, (3) Turing proposes the imitation game, (4) deep learning spreads widely.

  1. 2, 3, 1, 4
  2. 3, 2, 4, 1
  3. 3, 1, 2, 4
  4. 3, 2, 1, 4
Answer and explanation

Answer: D

Turing's paper is 1950 (3), Dartmouth is 1956 (2), Deep Blue is 1997 (1), and deep learning spreads from around the 2010s (4). Order: 3, 2, 1, 4.

A student says: 'Because a chess computer can beat a world champion, it is general AI.' What is wrong?

  1. A chess computer is narrow AI: excellent at chess but unable to do unrelated tasks
  2. Nothing; beating a champion proves general intelligence
  3. Chess computers are not AI at all
  4. General AI only plays board games
Answer and explanation

Answer: A

General AI would handle any intellectual task. A chess program excels only at chess and cannot, say, translate or drive, so it is narrow AI.

Which of these is the best example of AI rather than a fixed-rule program?

  1. A geyser that switches off at a set temperature
  2. A lift that stops at the floor whose button is pressed
  3. A microwave timer that rings after two minutes
  4. A maps app that predicts a route's travel time from traffic patterns
Answer and explanation

Answer: D

Predicting travel time from past and live traffic patterns is judgement learned from data. The geyser, lift and timer each follow a single fixed rule with no learning or prediction.

Which pair is correctly matched?

  1. General AI - exists in everyday phones
  2. Narrow AI - also called weak AI
  3. Strong AI - another name for narrow AI
  4. Weak AI - can do any intellectual task a human can
Answer and explanation

Answer: B

Narrow AI is also called weak AI: it does one task or a small set of tasks. General AI (strong AI, AGI) would handle any intellectual task and has not been achieved, so the other pairs are wrong.

A fraud filter flags 50 payments: 42 are real fraud and 8 are genuine. It also lets 5 real frauds through. How many real frauds were there in total?

  1. 42
  2. 50
  3. 47
  4. 55
Answer and explanation

Answer: C

Real frauds = frauds caught + frauds missed = 42 + 5 = 47. The 8 genuine payments flagged are false positives and are not counted as fraud.

Why should a human check AI output before using it for an important decision?

  1. AI can make errors, lacks context and cannot be held accountable
  2. AI output is always written in a foreign language
  3. Checking makes the AI run faster
  4. The law says AI may never be used
Answer and explanation

Answer: A

AI can be wrong, can miss context a person would notice, and cannot take responsibility. A person catches errors and owns the final decision.

A face-recognition system trained mostly on photos of one group of people works poorly for others. This problem is called:

  1. Inference
  2. Bias
  3. Reinforcement
  4. Encryption
Answer and explanation

Answer: B

Unfair, uneven results caused by unbalanced training data are bias. The fix starts with more balanced, representative data and human review.

A fraud filter blocks a customer's genuine payment as suspicious. This is a:

  1. False negative
  2. Hallucination
  3. True positive
  4. False positive
Answer and explanation

Answer: D

The system said 'fraud' (positive) when the truth was 'not fraud', so it is a false positive. A false negative would be a real fraud let through.

In AI, 'hallucination' means:

  1. The AI system switching itself off
  2. A camera seeing images in the dark
  3. The AI giving confident but false or made-up information
  4. A virus attacking the AI
Answer and explanation

Answer: C

Hallucination is when an AI system, especially a chatbot, produces fluent, confident output that is false or invented, such as a fake reference or a wrong date.

Privacy · Terms · Refunds · Delivery