Deck 15: Artificial Intelligence

Question 1

Any knowledge representation scheme we select must be relatively easy to extend to include new knowledge.

Answer 1

True

Question 2

The ____ test tests to see if a machine exhibits behavior indistinguishable from a human.

A) computer intelligence
B) AI
C) Turing
D) cognitive

Answer 2

C

Question 3

Cause and effect relationships are translated into "for every" statements. _________________________

Answer 3

False
if-then
if then

Question 4

In a neural network, both the knowledge representation and also the "programming" are stored in the network itself as the weights of the connections and the thresholds of the neurons.

Question 5

Proponents of the reactive strategy of robotics argue that a robot cannot react meaningfully without processing the stimulus and planning a reaction based on its internal representation of the environment. _________________________

Question 6

Backward chaining begins with assertions and tries to match those assertions to the "if" clauses of rules, thereby generating new assertions. _________________________

Question 7

Building a machine that can beat a human at chess is definitively the supreme test of artificial of intelligence.

Question 8

The term ____ means the language of formal logic.

A) graphical scheme
B) natural language
C) logic scheme
D) formal language

Question 9

A robot must not only gather sensory information, but filter out the possibly vast amount of data its surroundings might present to it.

Question 10

The human brain uses a ____ architecture, characterized by a large number of simple "processors" with multiple interconnections.

A) neural
B) network
C) connectionist
D) Victorian

Question 11

A formal language representation has the disadvantage of extracting the essentials.

Question 12

A brute force approach is commonly used for intelligent chess-playing strategy.

Question 13

Computational tasks are tasks for which accurate answers need not be found. _________________________

Question 14

Computers fall below humans where there seems to be a high level of complexity and perhaps approximation or ambiguity.

Question 15

____ is the branch of computer science that explores techniques for incorporating aspects of intelligence into computer systems.

A) Internet technology
B) Neural networks
C) Database technology
D) Artificial intelligence

Question 16

____ is the study of how we as humans think and learn.

A) Artificial intelligence
B) Cognitive science
C) Social science
D) Neuroscience

Question 17

If an output neuron fires when it is not supposed to, then the positive input values coming into it are adjusted upward. _________________________

Question 18

Complex recognition tasks are easy for computers to perform.

Question 19

A neuron is a cell capable of receiving stimuli, in the form of electrochemical signals, from other neurons through its many dendrites.

Question 20

In some areas of the brain, an individual neuron may collect signals from as many as 100,000 other neurons and send signals to equally large number of other neurons.

Question 21

A(n) ____ is a form of software technology that is designed to interact collaboratively with a user somewhat in the mode of a personal assistant.

A) intelligent agent
B) wizard
C) knowledge-based system
D) rule-based system

Question 22

A(n) ____ attempts to mimic the human ability to engage pertinent facts and string them together in a logical fashion to reach some conclusion.

A) inference engine
B) back propagation system
C) intelligent agent
D) rule-based system

Question 23

A(n) ____ begins to not merely wait for user commands but initiates communication, takes action, and performs tasks on its own on the basis of its increasing knowledge of your needs and preferences.

A) personalized Web server
B) intelligent agent
C) computer personal assistant
D) wizard

Question 24

A(n) ____ approach for a solution path traces all branches of the state-space graph so that all possible choices are tested and no test cases are repeated.

A) heuristic
B) push technology
C) intelligent
D) brute force

Question 25

Each ____________________ can be thought of as an extremely simple computational device with a single on/off output.

Question 26

A ____ for a search algorithm illustrates the possible next choices of items to search if the current item is not the target.

A) back propagation algorithm
B) connectionist architecture
C) training data
D) decision tree

Question 27

A neural network is presented with ____, for which the correct outputs are known.

A) training data
B) base data
C) correct information
D) weights

Question 28

The term ____ means "method of assertion."

A) QED
B) forward chaining
C) knowledge engineering
D) modus ponens

Question 29

Prolog is a(n) ____________________ programming language.

Question 30

The ____ causes the network to settle into a stable state where it can correctly respond, to any desired degree of accuracy, to all inputs in the training set.

A) back propagation algorithm
B) decision tree
C) connectionist architecture
D) solution path

Question 31

Intelligent searching involves applying some ____ to evaluate the differences between the present state and the goal state, and to move us to a new state that minimizes those differences.

A) heuristic
B) brute force
C) swarm intelligence
D) back propagation

Question 32

A(n) ____ contains facts about a specific subject domain to narrow the scope to a manageable size.

A) explanation facility
B) modus ponens
C) knowledge base
D) intelligent agent

Question 33

A(n) ____________________ language sacrifices richness of expression for precision of expression.

Question 34

At periodic time intervals, ____ technology downloads updated, personalized information on your screen.

A) search engine
B) push
C) spider
D) wizard

Question 35

____________________ with a hidden layer of neurons are useful for recognition tasks, where we desire a certain pattern of output signals for a certain pattern of input signals.

Question 36

____ begins with assertions and tries to match those assertions to the "if" clauses of rules.

A) Decision making
B) Backward chaining
C) Knowledge engineering
D) Forward chaining

Question 37

A ____ takes us from the initial state to a winning configuration, and the graph nodes along the way represent the intermediate configurations.

A) heuristic
B) brute force approach
C) solution path
D) state-space graph

Question 38

We seek to perform a(n) ____ to find a solution path through the graph.

A) decision tree search
B) state-space search
C) graph traversal
D) intelligent search

Question 39

Although ____________________ incorporate a body of knowledge to "filter" their choices and thereby appear to capture certain aspects of human reasoning, they still perform relatively limited tasks.

Question 40

____ is a well-known humanoid robot built by Honda Motor Company.

A) ROBOTO
B) ISSAC
C) ASIMO
D) CIVIC

Question 41

What does the term robot imply?

Question 42

What does the Turing test allow?

Question 43

Describe the strategies that characterize robotics research.

Question 44

It has been said of intelligent agent technology that once a sufficient level of trust has been achieved, and when human users are willing to allow their software to make independent decisions, we will begin to see exciting new applications. List one.

Question 45

Explain each of the ways in which inference engines for expert systems can proceed.

Question 46

Explain the characteristics that any knowledge representation scheme that we select must have.

Question 47

What are the required components of an expert system?

Question 48

Provide at least three examples of an intelligent agent.

Question 49

Explain in detail what swarm intelligence is.

Question 50

What is the brute force approach, in terms of a solution path?