Neural Network

Analysis of Pattern Storage

Question 1
Marks : +2 | -2
Pass Ratio : 100%
In a linear autoassociative network, if input is noisy than output will be noisy?
yes
no
Explanation:
Linear autoassociative network gives out, what is given to it as input.
Question 2
Marks : +2 | -2
Pass Ratio : 100%
When are stable states reached in energy landscapes, that can be used to store input patterns?
mean of peaks and valleys
maxima
minima
none of the mentioned
Explanation:
Energy minima corresponds to stable states that can be used to store input patterns.
Question 3
Marks : +2 | -2
Pass Ratio : 100%
What happens when number of available energy minima be more than number of patterns to be stored?
no effect
pattern storage is not possible in that case
error in recall
none of the mentioned
Explanation:
Due to additional false minima, there is error in recall.
Question 4
Marks : +2 | -2
Pass Ratio : 100%
What happens when number of available energy minima be less than number of patterns to be stored?
pattern storage is not possible in that case
pattern storage can be easily done
pattern storage problem becomes hard problem for the network
none of the mentioned
Explanation:
Pattern storage problem becomes hard problem, when number of energy minima i.e stable states are less.
Question 5
Marks : +2 | -2
Pass Ratio : 100%
How hard problem can be solved?
by providing additional units in a feedback network
nothing can be done
by removing units in hidden layer
none of the mentioned
Explanation:
Hard problem can be solved by providing additional units in a feedback network.
Question 6
Marks : +2 | -2
Pass Ratio : 100%
Does linear autoassociative network have any practical use?
yes
no
Explanation:
Since if input is noisy then output will aslo be noisy, hence no practical use.
Question 7
Marks : +2 | -2
Pass Ratio : 100%
What can be done by using non – linear output function for each processing unit in a feedback network?
pattern classification
recall
pattern storage
all of the mentioned
Explanation:
By using non – linear output function for each processing unit, a feedback network can be used for pattern storage.
Question 8
Marks : +2 | -2
Pass Ratio : 100%
The number of patterns that can be stored in a given network depends on?
number of units
strength of connecting links
both number of units and strength of connecting links
none of the mentioned
Explanation:
The number of patterns that can be stored in a given network depends on number of units and strength of connecting links.
Question 9
Marks : +2 | -2
Pass Ratio : 100%
Why there is error in recall, when number of energy minima is more the required number of patterns to be stored?
due to noise
due to additional false maxima
due to additional false minima
none of the mentioned
Explanation:
Due to additional false minima, there is error in recall.
Question 10
Marks : +2 | -2
Pass Ratio : 100%
Which is a simplest pattern recognition task in a feedback network?
heteroassociation
autoassociation
can be hetero or autoassociation, depends on situation
none of the mentioned
Explanation:
Autoassociation is the simplest pattern recognition task.