Artificial Intelligence Questions and Answers Set 3

Artificial Intelligence

Questions 21 to 30

21.
Which is not a desirable property of a logical rule-based system?
(a)  Locality                                            (b)  Attachment                     (c)  Detachment
(d)  Truth-Functionality                            (e)  Global attribute.
22.
How is Fuzzy Logic different from conventional control methods?
(a)  IF and THEN Approach                      (b)  FOR Approach
(c)  WHILE Approach                                                            (d)  DO Approach
(e)  Else If approach.
23.
In an Unsupervised learning
(a)   Specific output values are given
(b)   Specific output values are not given
(c)   No specific Inputs are given
(d)   Both inputs and outputs are given
(e)   Neither inputs nor outputs are given.
24.
Inductive learning involves finding a
(a)  Consistent Hypothesis                      (b)  Inconsistent Hypothesis
(c)  Regular Hypothesis                           (d)  Irregular Hypothesis
(e)  Estimated Hypothesis.
25.
Computational learning theory analyzes the sample complexity and computational complexity of
(a)  UnSupervised Learning                      (b)  Inductive learning
(c)  Forced based learning                       (d)  Weak learning
(e)  Knowledge based learning.
26.
If a hypothesis says it should be positive, but in fact it is negative, we call it
(a)  A consistent hypothesis                    (b)  A false negative hypothesis
(c)  A false positive hypothesis                (d)  A specialized hypothesis
(e)  A true positive hypothesis.
27.
Neural Networks are complex -----------------------with many parameters.
(a)  Linear Functions                               (b)  Nonlinear Functions
(c)  Discrete Functions                            (d)  Exponential Functions
(e)  Power Functions.
28.
A perceptron is a --------------------------------.
(a)  Feed-forward neural network              (b)  Back-propagation alogorithm
(c)  Back-tracking algorithm                     (d)  Feed Forward-backward algorithm
(e)  Optimal algorithm with Dynamic programming.
29.
Which is true?
(a)   Not all formal languages are context-free
(b)   All formal languages are Context free
(c)   All formal languages are like natural language
(d)   Natural languages are context-oriented free
(e)   Natural language is formal.
30.
Which is not true?
(a)   The union and concatenation of two context-free languages is context-free
(b)   The reverse of a context-free language is context-free, but the complement need not be
(c)   Every regular language is context-free because it can be described by a regular grammar
(d)   The intersection of a context-free language and a regular language is always context-free
(e)   The intersection two context-free languages is context-free.

Answers


21.
Answer : (b)
Reason : Locality: In logical systems, whenever we have a rule of the form A => B, we can conclude B, given evidence A, without worrying about any other rules. Detachment: Once a logical proof is found for a proposition B, the proposition can be used regardless of how it was derived .That is, it can be detachment from its justification. Truth-functionality: In logic, the truth of complex sentences can be computed from the truth of the components. But there are no Attachment properties lies in a Rule-based system. Global attribute defines a particular problem space as user specific and changes according to user’s plan to problem.
22.
Answer : (a)
Reason : FL incorporates a simple, rule-based IF X AND Y THEN Z approach to a solving control problem rather than attempting to model a system mathematically. The FL model is empirically-based, relying on an operator's experience rather than their technical understanding of the system. For example, rather than dealing with temperature control in terms such as "SP =500F", "T <1000F", or "210C <TEMP <220C", terms like "IF (process is too cool) AND (process is getting colder) THEN (add heat to the process)" or "IF (process is too hot) AND (process is heating rapidly) THEN (cool the process quickly)" are used. These terms are imprecise and yet very descriptive of what must actually happen. Consider what you do in the shower if the temperature is too cold: you will make the water comfortable very quickly with little trouble. FL is capable of mimicking this type of behavior but at very high rate.
23.
Answer : (b)
Reason : The problem of unsupervised learning involves learning patterns in the input when no specific out put values are supplied. We can not expect the specific output to test your result. Here the agent does not know what to do, as he is not aware of the fact what propose system will come out. We can say an ambiguous unproposed situation.
24.
Answer : (a)
Reason : Inductive learning involves finding a consistent hypothesis that agrees with examples. The difficulty of the task depends on the chosen representation.
25.
Answer : (b)
Reason : Computational learning theory analyzes the sample complexity and computational complexity of inductive learning. There is a trade off between the expressiveness of the hypothesis language and the ease of learning.
26.
Answer : (c)
Reason : Consistent hypothesis go with examples, If the hypothesis says it should be negative but infact it is positive, it is false negative. If a hypothesis says it should be positive, but in fact it is negative, it is false positive. In a specialized hypothesis we need to have certain restrict or special conditions.
27.
Answer : (b)
Reason : Neural networks parameters can be learned from noisy data and they have been used for thousands of applications, so it varies from problem to problem and thus use nonlinear functions.
28.
Answer : (a)
Reason : A perceptron is a Feed-forward neural network with no hidden units that can be represent only linear separable functions. If the data are linearly separable, a simple weight updated rule can be used to fit the data exactly.
29.
Answer : (a)
Reason : Not all formal languages are context-free — a well-known counterexample is
              This particular language can be generated by a parsing expression grammar, which is a relatively new formalism that is particularly well-suited to programming languages.
30.
Answer : (e)
Reason : The union and concatenation of two context-free languages is context-free; but intersection need not be.

<< Prev  1 ...  2 ...  3 ...  4 ...  5 ...  6 ...  Next  >>


1 comment :

  1. A perceptron is a Feed-forward neural network with no hidden units that can be represent only linear separable functions. If the data are linearly separable, a simple weight updated rule can be used to fit the data exactly.speech recognition software

    ReplyDelete