+1-315-636-4485
+91 98151-74050 
This quiz contains multiple-choice problems on the feedback layer and feature mapping network analysis.
How are input layer units connected to the second layer in competitive learning networks?
Feedforward manner
Feedback manner
Feedforward and feedback
Feedforward or feedback
Which layer has feedback weights in competitive neural networks?
Input layer
Second layer
Both input and second layer
None of the above
What is the nature of general feedback given in competitive neural networks?
Self-excitatory
Self-inhibitory
Self-excitatory or self-inhibitory
None of the above
What consists of competitive learning neural networks?
Feedforward paths
Feedback paths
Either feedforward or feedback
Combination of feedforward and feedback
What are the necessary conditions for competitive networks to perform pattern clustering?
Non-linear output layers
Connection to neighbours is excitatory and to the farther units inhibitory
On centre off surround connections
None of the above
What are the necessary conditions for competitive networks to perform feature mapping?
Non-linear output layers
Connection to neighbours is excitatory and to the farther units inhibitory
On centre off surround connections
None of the above
If a competitive network can perform feature mapping, what is that network called?
Self-excitatory
Self-inhibitory
Self organization
None of the above
What is an instar?
It receives inputs from all others
It gives output to all others
It may receive or give input or output to others
None of the above
How is the weight vector adjusted in basic competitive learning?
Such that it moves towards the input vector
Such that it moves away from input vector
Such that it moves towards the output vector
Such that it moves away from output vector
The update in the weight vector in basic competitive learning can be represented by
w(t + 1) = w(t) + del.w(t)
w(t + 1) = w(t)
w(t + 1) = w(t) – del.w(t)
None of the above
What kind of learning is involved in the pattern clustering task?
Supervised
Unsupervised
Learning with critic
None of the above
Does the physical location of a unit relative to another unit have any significance on pattern clustering?
Yes
No
Depends on type of clustering
None of the above
How are feature mapping networks distinct from competitive learning networks?
Geometrical arrangement
Significance attached to neighbouring units
Non-linear units
None of the above
What is the objective of feature maps?
To capture the features in space of input patterns
To capture just the input patterns
To update weights
To capture output patterns
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 above
