Ai6

Question 1

What does AI stand for?

Answer 1

Artificial Intelligence

Question 2

True or False: AI is only used for robots.

Answer 2

False

Question 3

What does ML stand for in AI?

Answer 3

Machine Learning

Question 4

What is the main difference between AI and ML?

Answer 4

Simple example:
AI: A robot that can clean your house and chat with you.
ML: The part of that robot that learns which rooms get dirty fastest based on past cleaning data.

Question 5

What does NLP stand for?

Answer 5

Natural Language Processing

Question 6

Fill in the blank: NLP helps computers understand ________.

Answer 6

human language

Question 7

What does API stand for?

Answer 7

Application Programming Interface

Question 8

Which best describes an API?

Answer 8

“A set of rules that lets software programs communicate with each other”

Question 9

True or False: LLM stands for Long Language Machine.

Answer 9

False

Question 10

What’s is an LLM

Answer 10

An LLM (Large Language Model) is a type of AI trained on huge amounts of text so it can understand and generate human language.

How to remember it:
Think of an LLM like a giant reservoir filled with words. When you ask it something, it draws from that reservoir — like turning on a tap — and gives you a stream of language instead of water.

Question 11

What does SDK stand for?

Answer 11

Software Development Kit

Question 12

Fill in the blank: An SDK gives developers the ________ they need to build software.

Answer 12

An SDK (Software Development Kit) gives developers the tools, libraries, documentation, and code samples they need to build software for a specific platform or framework.

Question 13

What does a vector database store?

Answer 13

Numbers that represent meaning, used for fast AI search.

Question 14

What is a common use of embeddings in AI?

Answer 14

To compare the meaning or similarity between words, documents, or images by converting them into numerical vectors that capture semantic relationships — like plotting ideas on a map, where similar meanings are closer together.

Question 15

Fill in the blank: A chatbot like ChatGPT is powered by a ______.

Answer 15

Large Language Model (LLM)

Question 16

What is the goal of a classification problem in AI?

Answer 16

To sort data into categories, like spam vs not spam.

Detailed explanation:- To automatically assign input data to one of several predefined categories or classes based on patterns learned from labelled training data. For example, identifying whether an email is spam or not spam, or classifying images of animals into categories like cats, dogs, or birds.

Question 17

Regression problems are used when you want to predict a ________.

Answer 17

number

Question 18

True or False: An AI that predicts house prices is likely using regression.

Answer 18

True

Question 19

What is the main role of training data?

Answer 19

To help the AI learn by showing examples.

Question 20

What does RAG stand for?

Answer 20

Retrieval-Augmented Generation

Question 21

Fill in the blank: RAG helps combine LLMs with your own ________.

Answer 21

data

Question 22

What is the purpose of prompt engineering?

Answer 22

To write better inputs that guide an AI to give useful answers.

Question 23

True or False: Prompt engineering only works with voice assistants.

Answer 23

False

Question 24

What is supervised learning?

Answer 24

Learning from data that includes correct answers.

Question 25

What is unsupervised learning?

Answer 25

Learning from data without labels, finding patterns.

Question 26

What is an example of classification?

Answer 26

Classification is when an AI model assigns inputs into predefined categories. A common example is classifying emails as “spam” or “not spam”. Other examples include identifying whether an image contains a cat or a dog, predicting if a customer is likely to churn or stay, or determining the sentiment of a product review as positive, negative, or neutral.

Question 27

What is overfitting in AI?

Answer 27

When a model learns training data too well and fails on new data.

Question 28

True or False: Overfitting means the model performs well on unseen data.

Answer 28

False

Question 29

Fill in the blank: A neural network is made up of many connected ________.

Answer 29

layers

Question 30

What does 'inference' mean in AI?

Answer 30

Using what the model learned to make predictions.

Question 31

Which of these is an example of inference in the context of AI? A. A model is trained on a dataset of cat and dog images. B. A model predicts an email is spam based on its content. C. A dataset is cleaned and labelled. D. A neural network is being designed.

Answer 31

B. A model predicts an email is spam based on its content. ⸻ Inference in AI refers to the process of using a trained model to make predictions or decisions based on new data. Option B is the only one where the model is applying what it has learned—i.e., performing inference.

Question 32

What is an embedding?

Answer 32

A number-based representation of something like a word or image.

Question 33

Fill in the blank: Embeddings help AI understand ________ rather than just exact words.

Answer 33

meaning

Question 34

True or False: A vector database can help an AI find similar documents.

Answer 34

True

Question 35

What does it mean to label data?

Answer 35

To mark examples with the correct answers for training.

Question 36

Which of these is unsupervised learning? A) Sentiment analysis B) Clustering customers by behaviour C) Image recognition

Answer 36

B) Clustering customers by behaviour Explanation: Unsupervised learning finds patterns in unlabelled data. Clustering groups similar customers without pre-defined labels.

Question 37

What’s the difference between training and inference?

Answer 37

Training is learning from data, inference is using what it learned.

Question 38

Fill in the blank: Classification sorts things into categories, while regression predicts a ________.

Answer 38

number

Question 39

What is a real-world example of classification?

Answer 39

A bank deciding if a loan application is low or high risk.

Question 40

What’s a real-world example of regression?

Answer 40

Estimating the price of a used car based on age and mileage.

Question 41

True or False: A model trained with supervised learning doesn’t need labelled data.

Answer 41

False

Question 42

What’s the main job of a neural network?

Answer 42

To process information and find patterns in data.

Question 43

True or False: An LLM like ChatGPT needs no training data.

Answer 43

False

Question 44

What is fine-tuning?

Answer 44

Adjusting an AI model using your own data to make it more accurate. Example: A company might fine-tune a general language model like GPT to better handle their customer service queries by training it on past chat transcripts.

Question 45

What’s a real-world example of RAG?

Answer 45

Using ChatGPT to answer questions based on company documents.

Question 46

Why do AI models use so much data?

Answer 46

Because more data helps them learn patterns more accurately.

Question 47

What is a variable in Python?

Answer 47

A name used to store a value, like a label for information.

Question 48

Fill in the blank: In Python, name = 'Andrew' is storing the word 'Andrew' in a ________ called name.

Answer 48

variable

Question 49

What is a Python function?

Answer 49

A block of code that does something. You can use it again and again.

Question 50

True or False: Functions can take inputs and return outputs.

Answer 50

True

Question 51

What does a for loop do in Python?

Answer 51

It repeats an action for each item in a list or sequence.

Question 52

What is a list in Python?

Answer 52

An ordered group of items, written in square brackets.

Question 53

What is a dictionary in Python?

Answer 53

A group of key-value pairs, like a contact list.

Question 54

True or False: Python is the most popular language for AI.

Answer 54

True

Question 55

What is a Jupyter notebook used for?

Answer 55

Writing, testing, and sharing code — often used for data science and AI.

Question 56

What is Hugging Face?

Answer 56

A website where you can find and use AI models.

Question 57

What is AutoML?

Answer 57

Tools that help people build machine learning models without much coding.

Question 58

Fill in the blank: The 'OpenAI API' lets you send ________ to an AI model and get answers.

Answer 58

prompts

Question 59

What is tokenisation in AI?

Answer 59

Breaking text into small pieces (tokens) so an AI can understand it.

Question 60

True or False: AI models charge based on the number of tokens used.

Answer 60

True

Question 61

What does 'context window' mean for an LLM?

Answer 61

The maximum amount of info it can remember at once.

Question 62

What does 'inference cost' mean?

Answer 62

How much it costs to run an AI model on new data.

Question 63

Final Q: What’s the main benefit of understanding these fundamentals?

Answer 63

So you can use AI more effectively in real life, even without being a programmer.