Determination of Weights

Question 1
Marks : +2 | -2
Pass Ratio : 13%
what are affine transformations?
addition of bias term (-1) which results in arbitrary rotation, scaling, translation of input pattern.
none of the mentioned
addition of bias term (-1) or (+1) which results in arbitrary rotation, scaling, translation of input pattern.
Explanation:
It follows from basic definition of affine transformation.
Question 2
Marks : +2 | -2
Pass Ratio : 13%
In determination of weights by learning, for orthogonal input vectors what kind of learning should be employed?
hebb learning law
widrow learning law
hoff learning law
no learning law
Explanation:
For orthogonal input vectors, Hebb learning law is best suited.
Question 3
Marks : +2 | -2
Pass Ratio : 13%
What is the features that cannot be accomplished earlier without affine transformations?
arbitrary rotation
scaling
translation
all of the mentioned
Explanation:
Affine transformations can be used to do arbitrary rotation, scaling, translation.
Question 4
Marks : +2 | -2
Pass Ratio : 13%
In determination of weights by learning, for noisy input vectors what kind of learning should be employed?
hebb learning law
widrow learning law
hoff learning law
no learning law
Explanation:
For noisy input vectors, there is no learning law.
Question 5
Marks : +2 | -2
Pass Ratio : 13%
In determination of weights by learning, for linear input vectors what kind of learning should be employed?
hebb learning law
widrow learning law
hoff learning law
no learning law
Explanation:
For linear input vectors, widrow learning law is best suited.
Question 6
Marks : +2 | -2
Pass Ratio : 13%
By using only linear processing units in output layer, can a artificial neural network capture association if input patterns is greater then dimensionality of input vectors?
yes
no
Explanation:
There is need of non linear processing units.
Question 7
Marks : +2 | -2
Pass Ratio : 13%
Can a artificial neural network capture association if input patterns is greater then dimensionality of input vectors?
yes
no
Explanation:
By using nonlinear processing units in output layer.
Question 8
Marks : +2 | -2
Pass Ratio : 25%
For noisy input vectors, Hebb methodology of learning can be employed?
yes
no
Explanation:
For noisy input vectors, no specific type of learning method exist.
Question 9
Marks : +2 | -2
Pass Ratio : 13%
What are the features that can be accomplished using affine transformations?
arbitrary rotation
scaling
translation
all of the mentioned
Explanation:
Affine transformations can be used to do arbitrary rotation, scaling, translation.
Question 10
Marks : +2 | -2
Pass Ratio : 13%
Number of output cases depends on what factor?
number of inputs
number of distinct classes
total number of classes
none of the mentioned
Explanation:
Number of output cases depends on number of distinct classes.