Artificial Intelligence questions

By Interwoven Maths

Artificial Intelligence question collection

Review Artificial Intelligence questions for Computer Science, with correct answers shown and coverage across AI and machine learning vocabulary; training data; bias and limitations.

Back to Artificial Intelligence practice Back to Computer Science

Question 1

What does AI stand for?
  1. Artificial Intelligence
  2. Automated Internet
  3. Applied Interface
  4. Array Instruction

Question 2

What are AI systems designed to do?
  1. Perform tasks associated with human intelligence
  2. Repeat fixed instructions without using data
  3. Store information without processing it
  4. Connect devices without analysing signals

Question 3

What is machine learning?
  1. Finding patterns in data to make predictions
  2. Following rules written for every possible input
  3. Storing examples without analysing them
  4. Labelling every future input by hand

Question 4

What is training data?
  1. Examples used to teach a model
  2. New examples reserved for testing
  3. Predictions produced after inference
  4. Instructions that draw the user interface

Question 5

What is a model in AI?
  1. A learned pattern used for predictions
  2. A collection of raw training examples
  3. A single prediction produced by a system
  4. A tool used to label examples manually

Question 6

What does inference mean in AI?
  1. Using a trained model to make a prediction
  2. Adjusting a model using training examples
  3. Comparing predictions with correct test labels
  4. Attaching correct labels to training examples

Question 7

What does NLP stand for?
  1. Natural Language Processing
  2. Network Logic Protocol
  3. Numeric List Processing
  4. Node Link Programming

Question 8

What is computer vision used for?
  1. Interpreting images and video
  2. Interpreting written language
  3. Converting speech into text
  4. Predicting numerical values

Question 9

What is a chatbot designed to do?
  1. Hold conversations in natural language
  2. Identify faces in images
  3. Recommend content from preferences
  4. Convert recorded speech to text

Question 10

What do recommendation systems do?
  1. Suggest products or content
  2. Assign data to named categories
  3. Convert recorded speech to text
  4. Identify faces in images

Question 11

What does classification do?
  1. Assigns data to named categories
  2. Predicts a numerical value
  3. Groups similar data without labels
  4. Creates new examples from a prompt

Question 12

What does speech recognition convert?
  1. Spoken words to text
  2. Text to pixels
  3. Images to audio
  4. Numbers to passwords

Question 13

What can AI bias cause?
  1. Systematic errors for some groups
  2. Random errors spread equally across groups
  3. Higher accuracy for every tested group
  4. More representative training examples

Question 14

In AI, what does accuracy measure?
  1. How often predictions are correct
  2. How fast internet is
  3. How many files are stored
  4. How many colours are used

Question 15

What does human oversight of AI mean?
  1. People check important AI decisions
  2. People supply examples for training
  3. Programmers write the original code
  4. Users enter data into the system

Question 16

What can generative AI do?
  1. Create new content
  2. Assign existing data to categories
  3. Measure a model's accuracy
  4. Check whether users gave consent

Question 17

Face unlock on a phone is an example of what?
  1. Facial recognition
  2. Database normalisation
  3. Binary shifting
  4. Spreadsheet lookup

Question 18

Which is an AI privacy concern?
  1. Collecting personal data without consent
  2. Producing unequal accuracy between groups
  3. Hiding the reasons for a decision
  4. Replacing tasks previously done by people

Question 19

What is an AI hallucination?
  1. A plausible-sounding but false output
  2. A correct answer copied from training data
  3. A model update approved by a person
  4. A prediction with a high accuracy score

Question 20

What should good training data be like?
  1. Representative, varied and accurately labelled
  2. Large but collected from one group
  3. Varied but labelled inconsistently
  4. Current but missing uncommon cases

Question 21

What can introduce bias into training data?
  1. Under-representing one group
  2. Separating training and test examples
  3. Checking labels for consistency
  4. Sampling across the relevant population

Question 22

Why should humans review important AI outputs?
  1. To catch errors and unsafe decisions
  2. To add the outputs to training data
  3. To make the model calculate faster
  4. To collect more personal information

Question 23

What is test data used for in machine learning?
  1. Evaluate a trained model on unseen examples
  2. Adjust the model's learned patterns
  3. Provide labels for the training examples
  4. Store predictions for the user interface

Question 24

What does labelled training data contain?
  1. Examples paired with correct categories
  2. Examples without any expected outputs
  3. Predictions made after deployment
  4. Instructions written for every input

Question 25

What does transparency mean for an AI system?
  1. Its decision process can be understood
  2. Its training data is publicly editable
  3. Its predictions are accepted without review
  4. Its source code runs without testing

Question 26

What is a prediction in machine learning?
  1. An output based on learned patterns
  2. A guaranteed future outcome
  3. A rule written directly by a programmer
  4. A copy of a training example

Question 27

Why should an AI system be tested with new data?
  1. To check whether it works beyond its training examples
  2. To increase the size of the training set
  3. To measure file compression
  4. To replace human review

Question 28

What is object detection designed to do?
  1. Identify objects and their positions in images
  2. Identify speakers and their words in recordings
  3. Group text documents by writing style
  4. Predict numerical values from a table

Question 29

Who should remain accountable for an important AI-assisted decision?
  1. The people or organisation using the system
  2. The model without any human owner
  3. The training examples stored by the system
  4. The computer hardware running the model

Question 30

Why might an AI recommendation be unsuitable?
  1. It may be based on incomplete or biased data
  2. It has been checked by an expert
  3. It uses complete and current data
  4. It matches the user’s stated needs

About this topic

Review Artificial Intelligence questions for Computer Science, with correct answers shown and coverage across AI and machine learning vocabulary; training data; bias and limitations.

This topic covers

Example question types