Neural Networks

Pattern Classification

Question 1
Marks : +2 | -2
Pass Ratio : 100%
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
Explanation:
A convex set is a set of points in M-dimensional space such that line joining any two points in the set lies entirely in region enclosed by the set.
Question 2
Marks : +2 | -2
Pass Ratio : 100%
Is it true that percentage of linearly separable functions will increase rapidly as dimension of input pattern space is increased?
yes
no
Explanation:
There is decrease in number of linearly separable functions as dimension of input pattern space is increased.
Question 3
Marks : +2 | -2
Pass Ratio : 100%
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
Explanation:
Linear separability of classes is the condition for convergence of weighs in perceprton learning.
Question 4
Marks : +2 | -2
Pass Ratio : 100%
As dimensionality of input vector increases, what happens to linear separability?
increases
decreases
no effect
doesn’t depend on dimensionality
Explanation:
Linear separability decreases as dimensionality increases.
Question 5
Marks : +2 | -2
Pass Ratio : 100%
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
Explanation:
Practically, number of units in second layer determines shape of dividing surface.
Question 6
Marks : +2 | -2
Pass Ratio : 100%
If the output produces nonconvex regions, then how many layered neural is required at minimum?
2
3
4
5
Explanation:
Adding one more layer of units to three layer can yield surfaces which can separate even nonconvex regions.
Question 7
Marks : +2 | -2
Pass Ratio : 100%
Intersection of convex regions in three layer network can only produce convex surfaces, is the statement true?
yes
no
Explanation:
Intersection of convex regions in three layer network can produce nonconvex regions.
Question 8
Marks : +2 | -2
Pass Ratio : 100%
If pattern classes are linearly separable then hypersurfaces reduces to straight lines?
yes
no
Explanation:
Hypersurfaces reduces to straight lines, if pattern classes are linearly separable.
Question 9
Marks : +2 | -2
Pass Ratio : 100%
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
Explanation:
Practically, number of units in third layer determines number of classes.
Question 10
Marks : +2 | -2
Pass Ratio : 100%
Intersection of linear hyperplanes in three layer network can only produce convex surfaces, is the statement true?
yes
no
Explanation:
Intersection of linear hyperplanes in three layer network can only produce convex surfaces.