Chapter 14

Question 1

Artificial Intelligence (AI)

Answer 1

Focused on studying human thought processes and recreating them with machines like computers

Question 2

Strong AI

Answer 2

Hypothetical AI that matches or exceeds human intelligence and can perform any intellectual task that humans can

Question 3

Weak AI (Narrow AI)

Answer 3

AI that performs a specific function, previously requiring human intelligence, and does so at human levels or better

Question 4

Algorithm

Answer 4

A set of clear steps to solve a problem or complete a task.

Question 5

Machine Learning (ML)

Answer 5

A type of artificial intelligence that allows systems to automatically learn and improve from experience without being explicitly programmed

Question 6

Supervised Learning

Answer 6

Giving the system data and expected outcome results

Question 7

Classification

Answer 7

When a computer learns to put things into groups based on their information

Question 8

Supervised Learning Classifications

Answer 8

Binary Classification
Multi-Class Classification
Multi-Label Classification
Imbalanced Classification

Question 9

Binary Classification

Answer 9

Only two possible groups for the data

Question 10

Multi-Class Classification

Answer 10

More than two groups for the data

Question 11

Multi-Label Classification

Answer 11

Each example can belong to more than one group at the same time

Question 12

Imbalanced Classification

Answer 12

Some groups (classes) have way more examples than others

Question 13

Semi-Supervised Learning

Answer 13

Giving small amounts of labelled data and large amount of unlabelled data

Question 14

Unsupervised Learning

Answer 14

Computer finds patterns in data on its own without labels or much help

Question 15

Reinforcement Learning

Answer 15

System learns to achieve a goal in an uncertain and complex environment

Question 16

Deep Learning

Answer 16

Artificial neural networks learn from large amounts of data

Question 17

Neural Network (NN)

Answer 17

Virtual “neurons” arranged in layers that work together to simulate the human brain, to solve problems or recognize patterns

Question 18

Node

Answer 18

Part of Neural Network that takes input, processes it, and produces an output

Question 19

Backpropagation

Answer 19

A supervised learning method used to update a model’s parameters to improve the accuracy of its predictions.

Question 20

Recurrent Neural Network (RNN)

Answer 20

A type of neural network that processes sequential or time-series data, where the network’s decision depends on previous outputs

Question 21

Convolutional Neural Network (CNN)

Answer 21

Neural network used to understand images by looking at parts like edges, curves, and colors, and then putting them together to figure out what the image shows

Question 22

Generative Adversarial Network (GAN)

Answer 22

Has 2 parts
Generator: Learns to create realistic data.
Discriminator: Learns to distinguish between real and generated (fake) data

Question 23

Computer Vision

Answer 23

The ability of systems to recognize objects, scenes, and activities in images

Question 24

Natural Language Processing (NLP)

Answer 24

The ability of systems to understand and process text the way humans do

Question 25

Speech Recognition

Answer 25

The ability of systems to automatically and accurately transcribe human speech

Question 26

Chatbot

Answer 26

A program that uses AI and natural language processing to simulate human conversation, either by voice or text

Question 27

Machine Learning Systems

Answer 27

Systems that perform new tasks accurately by learning from training data or historical data with known labels