Introduction to Artificial Intelligence Questions and Answers

Q: What is the primary purpose of a performance measure in agent design?

Everything else follows from the performance measure, so stating it carefully, in terms of what is actually wanted rather than what is easy to measure, is the most consequential decision in designing an agent. A measure that rewards the wrong thing produces a system that pursues it faithfully. Speed, resource use and human comparison are secondary evaluations. Specification gaming is the direct consequence of getting this step wrong, which is why it heads the PEAS checklist.

Q: Why should a performance measure describe outcomes rather than behaviour?

Telling a cleaning agent to sweep rewards sweeping rather than cleanliness, and an agent may sweep dirt about indefinitely, whereas rewarding a clean floor leaves it free to find the best method. Measuring outcomes is often harder rather than easier, and regulation is not the reason. Specifying what is wanted rather than how to achieve it is the principle behind declarative specification generally, and its violation is behind many of the field's more entertaining failures.

Q: Who coined the term artificial intelligence?

McCarthy proposed the name for the 1956 Dartmouth workshop, partly to distinguish the new field from cybernetics. Turing wrote about machine intelligence without using the phrase, Shannon contributed to the workshop and to information theory, and Wiener founded the cybernetics tradition the name was chosen to separate from. A field's name is often chosen for political as much as descriptive reasons, and this one is a clear example.

Q: What does an agent perceive its environment through?

An agent perceives through sensors and acts through actuators, and the pair defines its interface to the world. The performance measure evaluates its behaviour from outside, and an internal model is maintained by the agent from its percepts rather than being a source of them. Keeping the interface clear is what allows the same agent design to be applied to a robot, a software system or a person, which is the generality the framework was devised for.

Q: What does an agent act upon its environment through?

Actions are executed by actuators, whether motors, displays, network messages or database writes, and the environment changes in response. Sensors only read, the percept sequence is the history of what has been read, and a knowledge base is internal. The symmetry of sensors and actuators across every kind of agent, physical or software, is what makes the agent abstraction so widely applicable.

Q: What is a percept sequence?

The percept sequence is everything the agent has perceived to date, and in principle an agent's action is a function of it. A reflex agent uses only its last element, while a model based agent summarises the rest into internal state. The list of intended actions is a plan, and the environment's history is not directly available. Defining behaviour as a function of the whole history is what makes the framework fully general before any architecture is chosen.

Q: What is an agent function?

The agent function is the abstract mapping from every possible percept history to an action, while the agent program is the concrete implementation that realises it. The function may be an infinite table; the program must be finite. Distinguishing specification from implementation at the outset is what allows the same behaviour to be realised by very different architectures and compared fairly.

Q: What is the difference between an agent function and an agent program?

The function describes what the agent does in every possible circumstance, and the program is the finite artefact that computes it within the agent's resources. Two very different programs may implement the same function with different efficiency. Documentation, evaluation and synonymy are not the distinction. Separating what a system should do from how it does it is a principle borrowed from software engineering and it applies here with particular force.

71.

A system trained on data from one hospital performs poorly when deployed at another.

What is the most likely explanation?

A.The second hospital's computers are far slower than the first's
B.The training process was stopped before it had converged
C.Distribution shift between the two populations and practices
D.The model has too few parameters to represent the problem

Answer: C

Different patient populations, equipment and recording practices mean the deployed data differs from the training distribution, and the model's confident predictions become unreliable. Validating on data from the deployment site, and monitoring performance continuously, are the standard responses. Capacity, hardware and convergence would have shown up in the original evaluation. A failure that appears only on deployment points at the data rather than at the model.

Discuss in Forum

72.

What is the primary purpose of a performance measure in agent design?

A.It records how quickly the agent executes each of its actions
B.It measures the computing resources the agent consumes in use
C.It compares the agent with a human performing the same task
D.It defines what counts as success and so what the agent optimises

Answer: D

Everything else follows from the performance measure, so stating it carefully, in terms of what is actually wanted rather than what is easy to measure, is the most consequential decision in designing an agent. A measure that rewards the wrong thing produces a system that pursues it faithfully. Speed, resource use and human comparison are secondary evaluations. Specification gaming is the direct consequence of getting this step wrong, which is why it heads the PEAS checklist.

Discuss in Forum

73.

Why should a performance measure describe outcomes rather than behaviour?

A.Prescribing behaviour prevents the agent finding a better way
B.Behaviour is harder to observe than the resulting outcome
C.Outcomes are always easier to measure than actions taken
D.Regulations require that systems be specified by their outputs

Answer: A

Telling a cleaning agent to sweep rewards sweeping rather than cleanliness, and an agent may sweep dirt about indefinitely, whereas rewarding a clean floor leaves it free to find the best method. Measuring outcomes is often harder rather than easier, and regulation is not the reason. Specifying what is wanted rather than how to achieve it is the principle behind declarative specification generally, and its violation is behind many of the field's more entertaining failures.

Discuss in Forum

74.

Who is credited with proposing the imitation game?

A.Herbert Simon, who worked on symbol systems and decision making
B.Alan Turing
C.John McCarthy
D.Marvin Minsky, a founder of the Dartmouth workshop

Answer: B

Turing set out the imitation game in his 1950 paper on computing machinery and intelligence. McCarthy coined the term artificial intelligence six years later, and Minsky and Simon were among the founders of the field that followed. Attributing the foundational ideas to the right people matters because their differing views on what intelligence is still divide the subject, and each name is attached to a distinct position rather than merely to a date.

Discuss in Forum

75.

Who coined the term artificial intelligence?

A.Claude Shannon, in his work on information theory
B.Norbert Wiener
C.John McCarthy
D.Alan Turing, in his paper on computing machinery

Answer: C

McCarthy proposed the name for the 1956 Dartmouth workshop, partly to distinguish the new field from cybernetics. Turing wrote about machine intelligence without using the phrase, Shannon contributed to the workshop and to information theory, and Wiener founded the cybernetics tradition the name was chosen to separate from. A field's name is often chosen for political as much as descriptive reasons, and this one is a clear example.

Discuss in Forum

76.

What does an agent perceive its environment through?

A.Actuators, which also return information about the world
B.Its performance measure, which reports the state to it
C.Its internal model
D.Sensors

Answer: D

An agent perceives through sensors and acts through actuators, and the pair defines its interface to the world. The performance measure evaluates its behaviour from outside, and an internal model is maintained by the agent from its percepts rather than being a source of them. Keeping the interface clear is what allows the same agent design to be applied to a robot, a software system or a person, which is the generality the framework was devised for.

Discuss in Forum

77.

What does an agent act upon its environment through?

A.Actuators
B.Sensors, which both read and write to the environment
C.Its percept sequence, which determines the state directly
D.Its knowledge base

Answer: A

Actions are executed by actuators, whether motors, displays, network messages or database writes, and the environment changes in response. Sensors only read, the percept sequence is the history of what has been read, and a knowledge base is internal. The symmetry of sensors and actuators across every kind of agent, physical or software, is what makes the agent abstraction so widely applicable.

Discuss in Forum

78.

What is a percept sequence?

A.The sequence of states that the environment has passed through
B.The complete history of everything the agent has perceived
C.The single most recent observation the agent has received
D.The ordered list of actions the agent intends to perform

Answer: B

The percept sequence is everything the agent has perceived to date, and in principle an agent's action is a function of it. A reflex agent uses only its last element, while a model based agent summarises the rest into internal state. The list of intended actions is a plan, and the environment's history is not directly available. Defining behaviour as a function of the whole history is what makes the framework fully general before any architecture is chosen.

Discuss in Forum

79.

What is an agent function?

A.The performance measure by which the agent is judged
B.The model the agent maintains of its environment
C.A mapping from percept sequences to actions
D.The program that runs inside the agent's processor

Answer: C

The agent function is the abstract mapping from every possible percept history to an action, while the agent program is the concrete implementation that realises it. The function may be an infinite table; the program must be finite. Distinguishing specification from implementation at the outset is what allows the same behaviour to be realised by very different architectures and compared fairly.

Discuss in Forum

80.

What is the difference between an agent function and an agent program?

A.The function is written in code and the program is its documentation
B.The function evaluates performance and the program produces actions
C.There is no difference; the two terms are used interchangeably
D.The function is an abstract mapping and the program implements it

Answer: D

The function describes what the agent does in every possible circumstance, and the program is the finite artefact that computes it within the agent's resources. Two very different programs may implement the same function with different efficiency. Documentation, evaluation and synonymy are not the distinction. Separating what a system should do from how it does it is a principle borrowed from software engineering and it applies here with particular force.

Discuss in Forum

Loading…

Topics

Other Subjects

Tags: Introduction to Artificial Intelligence Questions and Answers || Introduction to Artificial Intelligence MCQ Questions and Answers || Introduction to Artificial Intelligence GK Questions and Answers || Introduction to Artificial Intelligence GK MCQ Questions || Introduction to Artificial Intelligence Multiple Choice Questions and Answers || Introduction to Artificial Intelligence GK || GK on Introduction to Artificial Intelligence || Artificial Intelligence Questions and Answers || Artificial Intelligence MCQ Questions and Answers || Artificial Intelligence GK Questions and Answers || GK on Artificial Intelligence

Introduction to Artificial Intelligence Questions and Answers

Topics

Other Subjects

About Us

Stay informed about all important Dates & Notifications