Expert Systems Questions and Answers

Q: Which measure did knowledge engineers use to judge whether a prototype was worth continuing?

A prototype of perhaps fifty rules was run against a handful of carefully chosen cases, and its behaviour on those decided whether the domain and the representation were viable. Rule counts, engine speed and vocabulary coverage measure effort rather than competence, and a system can accumulate all three while still answering badly. Judging by case performance early, before large investment, is the practical discipline that the rapid prototyping style of development was built around.

Q: Which difficulty arises when two experts disagree about a case?

Expert disagreement leaves the knowledge engineer arbitrating a question neither the formalism nor the engine can settle, and whichever view is encoded becomes the system's opinion. Conflict resolution will pick one rule, so no double answer appears, explanation reports whatever fired, and shells load contradictory rules without complaint. Measuring the extent of disagreement among experts is therefore part of validation, since a system cannot reasonably be held to a standard the experts themselves do not meet.

Q: Which practice reduces the risk that a knowledge base silently drifts out of date?

Annotating each rule with who supplied it, when and on what basis makes it possible to review the parts of the base a change in the domain has affected, instead of re-examining everything. Storage format and rule count do nothing for currency, and running the engine tests consistency rather than truth. Provenance is cheap to record at authoring time and almost impossible to reconstruct afterwards, which is why the discipline matters so much more in a knowledge base than in ordinary code.

Q: Which observation explains why expert systems remain in use in narrow settings?

In regulated settings such as tax, benefits and compliance, the rules are written down already, they change only by legislation, and every decision must be justifiable line by line. That is exactly the shape a rule base fits, and no learned model matches it for auditability. Build cost, hardware needs and user extensibility are not what keeps them alive. The survival of the technology in these niches, long after the general enthusiasm faded, is a good illustration of matching a method to the structure of its problem.

Q: DENDRAL rules are used to determine :

DENDRAL rules are used to determine complex chemical structures.DENDRAL, developed at Stanford from 1965 by Edward Feigenbaum, Joshua Lederberg and Bruce Buchanan, is regarded as the first expert system. It inferred the molecular structure of unknown organic compounds from mass spectrometry data, using heuristic rules supplied by chemists.It was not built for pharmaceutical, biological or geological structures; it worked out the structure of chemical molecules in general.

Q: Who is Domain expert ?

Of the options, the domain expert is the Doctor.In building an expert system, the domain expert is the person with deep knowledge of the problem area whose expertise is to be captured. In a medical diagnosis system such as MYCIN, that is the physician. A knowledge engineer interviews the expert and encodes the knowledge as rules.The software engineer and the programmer build the system, and the operator runs it; none of them supplies the domain knowledge.

Q: Which of the following statements is false for fuzzy expert systems ?

The false statement is Standard expert systems are always more appropriate than fuzzy expert systems.Fuzzy expert systems are designed for problems involving vague or imprecise knowledge, such as 'temperature is high', where crisp rules work poorly. Which kind of system is more appropriate depends on the problem, so 'always' makes the statement false.The other statements describe how a fuzzy expert system is actually built: first choose the linguistic variables, then generate fuzzy rules from the expert's knowledge using those variables, and build the system from that rule set with fuzzy inference.

101.

Which measure did knowledge engineers use to judge whether a prototype was worth continuing?

A.Its performance on a small set of representative cases
B.The number of rules it contained relative to the number the expert had originally estimated
C.The speed of its inference engine
D.The proportion of the domain vocabulary that had been captured in the frames written so far

Answer: A

A prototype of perhaps fifty rules was run against a handful of carefully chosen cases, and its behaviour on those decided whether the domain and the representation were viable. Rule counts, engine speed and vocabulary coverage measure effort rather than competence, and a system can accumulate all three while still answering badly. Judging by case performance early, before large investment, is the practical discipline that the rapid prototyping style of development was built around.

Discuss in Forum

102.

Which difficulty arises when two experts disagree about a case?

A.The shell will refuse to load a knowledge base in which two rules draw opposing conclusions
B.The knowledge base has no principled way to choose between them
C.The inference engine will fire both of the conflicting rules and produce two separate answers
D.The explanation facility cannot report either view

Answer: B

Expert disagreement leaves the knowledge engineer arbitrating a question neither the formalism nor the engine can settle, and whichever view is encoded becomes the system's opinion. Conflict resolution will pick one rule, so no double answer appears, explanation reports whatever fired, and shells load contradictory rules without complaint. Measuring the extent of disagreement among experts is therefore part of validation, since a system cannot reasonably be held to a standard the experts themselves do not meet.

Discuss in Forum

103.

Which practice reduces the risk that a knowledge base silently drifts out of date?

A.Increasing the number of rules
B.Running the inference engine over the whole knowledge base at regular intervals to test it
C.Recording the source and date of each rule
D.Storing the rules in a database rather than in a flat text file so that queries can be run

Answer: C

Annotating each rule with who supplied it, when and on what basis makes it possible to review the parts of the base a change in the domain has affected, instead of re-examining everything. Storage format and rule count do nothing for currency, and running the engine tests consistency rather than truth. Provenance is cheap to record at authoring time and almost impossible to reconstruct afterwards, which is why the discipline matters so much more in a knowledge base than in ordinary code.

Discuss in Forum

104.

Which observation explains why expert systems remain in use in narrow settings?

A.They are cheaper to build than a machine learning system trained on a comparable body of data
B.They run on modest hardware
C.They can be extended by the end users themselves without any assistance from a knowledge engineer
D.Encoded rules are auditable and stable

Answer: D

In regulated settings such as tax, benefits and compliance, the rules are written down already, they change only by legislation, and every decision must be justifiable line by line. That is exactly the shape a rule base fits, and no learned model matches it for auditability. Build cost, hardware needs and user extensibility are not what keeps them alive. The survival of the technology in these niches, long after the general enthusiasm faded, is a good illustration of matching a method to the structure of its problem.

Discuss in Forum

105.

DENDRAL rules are used to determine :

A.Pharmaceutical compound structures
B.Biological structures
C.Geological structures
D.Complex chemical structures

Exam Year(s)

MH SET - 2018, SET Exam - 2018,

Answer: D

DENDRAL rules are used to determine complex chemical structures.

DENDRAL, developed at Stanford from 1965 by Edward Feigenbaum, Joshua Lederberg and Bruce Buchanan, is regarded as the first expert system. It inferred the molecular structure of unknown organic compounds from mass spectrometry data, using heuristic rules supplied by chemists.

It was not built for pharmaceutical, biological or geological structures; it worked out the structure of chemical molecules in general.

Discuss in Forum

106.

Who is Domain expert ?

A.Software Engineer
B.Operator
C.Doctor
D.Programmer

Exam Year(s)

MH SET - 2018, SET Exam - 2018,

Answer: C

Of the options, the domain expert is the Doctor.

In building an expert system, the domain expert is the person with deep knowledge of the problem area whose expertise is to be captured. In a medical diagnosis system such as MYCIN, that is the physician. A knowledge engineer interviews the expert and encodes the knowledge as rules.

The software engineer and the programmer build the system, and the operator runs it; none of them supplies the domain knowledge.

Discuss in Forum

107.

Which of the following statements is false for fuzzy expert systems ?

A.First stage in building a fuzzy expert system is choosing suitable linguistic variables
B.Fuzzy expert system is built by creating a set of fuzzy rules applying fuzzy inference
C.Standard expert systems are always more appropriate than fuzzy expert systems.
D.Fuzzy rules are generated based on expert's knowledge, using linguistic variables.

Exam Year(s)

MH SET - 2018, SET Exam - 2018,

Answer: C

The false statement is Standard expert systems are always more appropriate than fuzzy expert systems.

Fuzzy expert systems are designed for problems involving vague or imprecise knowledge, such as 'temperature is high', where crisp rules work poorly. Which kind of system is more appropriate depends on the problem, so 'always' makes the statement false.

The other statements describe how a fuzzy expert system is actually built: first choose the linguistic variables, then generate fuzzy rules from the expert's knowledge using those variables, and build the system from that rule set with fuzzy inference.

Discuss in Forum

108.

Which amongst the following are essential components of an expert system ?

(i) Inference engine
(ii) Context graph
(iii) Knowledge base
(iv) Computer vision

A.(i) and (ii)
B.(i) and (iii)
C.(i), (ii) and (iii)
D.(ii), (iii) and (iv)

Exam Year(s)

MH SET - 2021, SET Exam - 2021,

Answer: B

The essential components are (i) and (iii), so the answer is (i) and (iii).

An expert system is built from a knowledge base, holding the facts and rules elicited from human experts, and an inference engine, which applies those rules to the facts of a case by forward or backward chaining to reach conclusions. A user interface and an explanation facility are usually added.

A context graph is not a standard component, and computer vision is a separate field of AI that an expert system does not need. Options including (ii) or (iv) are therefore wrong.

Discuss in Forum

109.

An expert system shell is an expert system without

A.domain knowledge
B.explanation facility
C.reasoning with knowledge
D.all of the above

Exam Year(s)

UGC NET - 2012,

Answer: A

An expert system shell is an expert system without domain knowledge. The shell has the inference engine, the explanation facility and the user interface, and it becomes an expert system when the knowledge base of a particular field is added. So the part that is missing from the shell is the domain knowledge. The shell still has the explanation facility and the ability to reason with knowledge. The keyed answer is domain knowledge.

Discuss in Forum

Loading…

Topics

Other Subjects

Tags: Expert Systems Questions and Answers || Expert Systems MCQ Questions and Answers || Expert Systems GK Questions and Answers || Expert Systems GK MCQ Questions || Expert Systems Multiple Choice Questions and Answers || Expert Systems GK || GK on Expert Systems || Artificial Intelligence Questions and Answers || Artificial Intelligence MCQ Questions and Answers || Artificial Intelligence GK Questions and Answers || GK on Artificial Intelligence

Expert Systems Questions and Answers

Topics

Other Subjects

About Us

Stay informed about all important Dates & Notifications