gs gs127 Feedforward Neural Networks - Pattern Classification - Quiz No.1
gs gs127 SQLite Quiz
This quiz belongs to book/course code gs gs127 SQLite of gs organization. We have 44 quizzes available related to the book/course SQLite. This quiz has a total of 20 multiple choice questions (MCQs) to prepare and belongs to topic Feedforward Neural Networks. NVAEducation wants its users to help them learn in an easy way. For that purpose, you are free to prepare online MCQs and quizzes.
NVAEducation also facilitates users to contribute in online competitions with other students to make a challenging situation to learn in a creative way. You can create one to one, and group competition on an topic of a book/course code. Also on NVAEducation you can get certifications by passing the online quiz test.
Question 1: What is the objective of perceptron learning?
class identification
weight adjustment
adjust weight along with class identification
none of the mentioned
Question 2: On what factor the number of outputs depends?
distinct inputs
distinct classes
both on distinct classes & inputs
none of the mentioned
Question 3: In perceptron learning, what happens when input vector is correctly classified?
small adjustments in weight is done
large adjustments in weight is done
no adjustments in weight is done
weight adjustments doesn’t depend on classification of input vector
Question 4: When two classes can be separated by a separate line, they are known as?
linearly separable
linearly inseparable classes
may be separable or inseparable, it depends on system
none of the mentioned
Question 6: Two classes are said to be inseparable when?
there may exist straight lines that doesn’t touch each other
there may exist straight lines that can touch each other
there is only one straight line that separates them
all of the mentioned
Question 8: The perceptron convergence theorem is applicable for what kind of data?
binary
bipolar
both binary and bipolar
none of the mentioned
Question 10: If e(m) denotes error for correction of weight then what is formula for error in perceptron learning model: w(m + 1) = w(m) + n(b(m) – s(m)) a(m), where b(m) is desired output, s(m) is actual output, a(m) is input vector and ‘w’ denotes weight
e(m) = n(b(m) – s(m)) a(m)
e(m) = n(b(m) – s(m))
e(m) = (b(m) – s(m))
none of the mentioned
Question 11: Convergence in perceptron learning takes place if and only if:
a minimal error condition is satisfied
actual output is close to desired output
classes are linearly separable
all of the mentioned
Question 12: When line joining any two points in the set lies entirely in region enclosed by the set in M-dimensional space , then the set is known as?
convex set
concave set
may be concave or convex
none of the mentioned
Question 15: As dimensionality of input vector increases, what happens to linear separability?
increases
decreases
no effect
doesn’t depend on dimensionality
Question 16: In a three layer network, shape of dividing surface is determined by?
number of units in second layer
number of units in third layer
number of units in second and third layer
none of the mentioned
Question 17: In a three layer network, number of classes is determined by?
number of units in second layer
number of units in third layer
number of units in second and third layer
none of the mentioned
