Chapter 14

Question 1

Artificial Intelligence (AI)

Answer 1

the theory and development of information systems that are capable of performing tasks that normally require human intelligence.

Question 2

Strong AI - also known as artificial general intelligence

Answer 2

a hypothetical artificial intelligence that matches or exceeds human intelligence

Question 3

Weak AI or Narrow AI

Answer 3

performs a useful and specific function that once required human intelligence to perform, and it does so at human levels or better.

Question 4

what are some technological advancements that have led to enhancements of AI

Answer 4

*Advancements in chip technology
*Big Data
*The internet and cloud computing
*Improved algorithms

Question 5

in the context of AI enabled crimes, what does the term “data poisoning” refer to?

Answer 5

An attach that manipulates a machine learning system’s training data set to control the predictive behaviour of a trained model.

Question 6

what are signs of intelligent behaviour?

Answer 6

*Learning from experience
*Responding successfully to new situations
*Making sense of ambiguous messages

Question 7

Machine Learning (ML)

Answer 7

an application of artificial intelligence that provides systems with the ability to automatically learn and improve from experience without being explicitly programmed.

Question 8

In supervised machine learning, how is the accuracy of the system evaluated?

Answer 8

By comparing the output to the expected results.

Question 9

Expert Systems (ES)

Answer 9

computer systems that attempt to mimic human experts by applying expertise in a specific domain.

Question 10

In expert systems, where is the knowledge typically stored?

Answer 10

In the form of IF-THEN rules

Question 11

what can the approach a develop takes to solve a problem reveal?

Answer 11

The developer’s bias

Question 12

What are the different types of machine learning?

Answer 12

*Supervised,
*Semi-Supervised
*Unsupervised
*Reinforcement
*Deep

Question 13

Supervised learning

Answer 13

a type of machine learning in which the systems is given labelled input data and the expected output results.

Question 14

what are the four types of of classification to a predictive modelling problem

Answer 14

*Binary classification
*Multi-class classification
*Multi-label classification
*Imbalanced Classification

Question 15

Binary classification

Answer 15

problems that have only two class labels

Question 16

Multi-class classification

Answer 16

classification problems with more than two class labels

Question 17

Multi-Label classification

Answer 17

classification problems that have two or more class labels.

Question 18

Imbalanced classification

Answer 18

the number of classes in each class is unequally distrubited.

Question 19

Linear regression

Answer 19

a supervised machine learning algorithm in which the predicted output is continuous and has a constant slope.

Question 20

Simple linear regresison

Answer 20

a single independent variable is used to predict the value of a dependent variable.

Question 21

Multiple linear regression

Answer 21

two or more independent variables are used to predict the value of a dependent variable.

Question 22

what is the purpose of using linear regression in supervised machine learning

Answer 22

to predict continuous variables.

Question 23

Semi-Supervised learning

Answer 23

type of machine learning that combines a small amount of labelled data with a large amount of unlabeled data during training.

Question 24

in the context of machine learning, why is it inefficient to have a human read through entire text documents to classify and label them?

Answer 24

Because it’s time-consuming and impractical with large amounts of data.

Question 25

Unsupervised learning

Answer 25

a type of machine learning that searches for previously undetected patterns in a data set with no pre-existing labels and with minimal human supervision.

Question 26

Cluster analysis, a primary technique in unsupervised learning, primarily used for?

Answer 26

Grouping data points to identify common characteristics.

Question 27

Reinforcement learning

Answer 27

type of machine learning in which the system learns to achieve a goal in an uncertain, potentially complex environment.

Question 28

What are some examples of reinforcement learning applications?

Answer 28

Recommendation systems Automated ad bidding and buying Dynamic resource allocation in wind farms, HVAC systems, and computer clusters in data centres *Automated calibration of engines and other machines *Robotic control *Autonomous vehicles such as self-driving cars *Supply chain optimization

Question 29

in reinforcement learning, the system begins with a totally random trials and ends with what

Answer 29

Sophisticated trials

Question 30

Deep learning

Answer 30

a subset of machine learning in which artificial intelligence neural networks learn from large amounts of data.

Question 31

Deep learning systems can be effective even when utilizing what kind of data set?

Answer 31

A diverse and unstructured data set

Question 32

Neural network

Answer 32

a set of virtual neurons or nodes that work in parallel to simulate the way the human brain works

Question 33

Node

Answer 33

a neural network has one or more weighted input connections, a bias, an activation function, and one or more output connections

Question 34

Activation functions

Answer 34

reside at each node define the output of that node given an input or a set of inputs

Question 35

backpropagation

Answer 35

the values of the weights of each pathway and the bias values of each node are slightly changed in anticipation that the next iteration of data flowing through the neural network will result In a smaller error, or loss, upon output.

Question 36

what does a loss function do in a neural network?

Answer 36

calculates the difference between the derived data value and the expected value

Question 37

Recurrent neural network

Answer 37

designed to access previous data such as sequential data or time series data during iterations of input.

Question 38

Convolutional neural network

Answer 38

designed to separate areas of image inputs by extracting features to identify edges, curves and colour density and then recombine these inputs for classification and prediction.

Question 39

Generative adversarial network

Answer 39

consists of two neural networks that compete with other in a zero-sum game in an effort to segregate real data from synthetic data.

Question 40

computer vision

Answer 40

refers to the ability of information systems to identify objects, scenes, and activities in images

Question 41

Natural language processing

Answer 41

the ability of information systems to work with text the way that humans do.

Question 42

in complex machine learning, which component adjusts thousands of times to accommodate new data inputs?

Answer 42

Weights and biases

Question 43

The shifting of weights and biases in the neural network is a process that

Answer 43

occurs over thousands of input values of iterations.