Neural Network

Analysis of Feature Mapping Network

Question 1
Marks : +2 | -2
Pass Ratio : 100%
In pattern clustering, does physical location of a unit relative to other unit has any significance?
yes
no
depends on type of clustering
none of the mentioned
Explanation:
Physical location of a unit doesn’t effect the output.
Question 2
Marks : +2 | -2
Pass Ratio : 100%
What kind of learning is involved in pattern clustering task?
supervised
unsupervised
learning with critic
none of the mentioned
Explanation:
Since pattern classes are formed on unlabelled classes.
Question 3
Marks : +2 | -2
Pass Ratio : 100%
In feature maps, when weights are updated for winning unit and its neighbour, which type learning it is known as?
karnaugt learning
boltzman learning
kohonen’s learning
none of the mentioned
Explanation:
Self organization network is also known as Kohonen learning.
Question 4
Marks : +2 | -2
Pass Ratio : 100%
In self organizing network, how is layer connected to output layer?
some are connected
all are one to one connected
each input unit is connected to each output unit
none of the mentioned
Explanation:
In self organizing network, each input unit is connected to each output unit.
Question 5
Marks : +2 | -2
Pass Ratio : 100%
How are weights updated in feature maps?
updated for winning unit only
updated for neighbours of winner only
updated for winning unit and its neighbours
none of the mentioned
Explanation:
Weights are updated in feature maps for winning unit and its neighbours.
Question 6
Marks : +2 | -2
Pass Ratio : 100%
Use of nonlinear units in the feedback layer of competitive network leads to concept of?
feature mapping
pattern storage
pattern classification
none of the mentioned
Explanation:
Use of nonlinear units in the feedback layer of competitive network leads to concept of pattern clustering.
Question 7
Marks : +2 | -2
Pass Ratio : 100%
What is true regarding adaline learning algorithm
uses gradient descent to determine the weight vector that leads to minimal error
error is defined as MSE between neurons net input and its desired output
this technique allows incremental learning
all of the mentioned
Explanation:
Incremental learning means refining of the weights as more training samples are added, rest are basic statements that defines adaline learning.
Question 8
Marks : +2 | -2
Pass Ratio : 100%
What is true for competitive learning?
nodes compete for inputs
process leads to most efficient neural representation of input space
typical for unsupervised learning
all of the mentioned
Explanation:
These all statements defines the competitive learning.
Question 9
Marks : +2 | -2
Pass Ratio : 100%
How is feature mapping network distinct from competitive learning network?
geometrical arrangement
significance attached to neighbouring units
nonlinear units
none of the mentioned
Explanation:
Both the geometrical arrangement and significance attached to neighbouring units make it distinct.
Question 10
Marks : +2 | -2
Pass Ratio : 100%
What is the objective of feature maps?
to capture the features in space of input patterns
to capture just the input patterns
update weights
to capture output patterns
Explanation:
The objective of feature maps is to capture the features in space of input patterns.