Applications of Neural Networks

Question 1
Marks : +2 | -2
Pass Ratio : 100%
What does the activation value of winner unit is indicative of?
greater the degradation more is the activation value of winning units
greater the degradation less is the activation value of winning units
greater the degradation more is the activation value of other units
greater the degradation less is the activation value of other units
Explanation:
Simply, greater the degradation less is the activation value of winning units.
Question 2
Marks : +2 | -2
Pass Ratio : 100%
Neuro – Fuzzy systems can lead to more powerful neural network?
yes
no
may be
cannot be determined
Explanation:
If fuzzy logic is incorporated into conventional ANN models, more powerful systems can be created.
Question 3
Marks : +2 | -2
Pass Ratio : 100%
Associative memory, if used in feedback structure of hopfield type can function as?
data memory
cluster
content addressable memory
none of the mentioned
Explanation:
Associative memory, if used in feedback structure of hopfield type can function as content addressable memory.
Question 4
Marks : +2 | -2
Pass Ratio : 100%
What are pros of neural networks over computers?
they have ability to learn b examples
they have real time high computational rates
they have more tolerance
all of the mentioned
Explanation:
Because of their parallel structure, they have high computational rates than conventional computers, so all are true.
Question 5
Marks : +2 | -2
Pass Ratio : 100%
Can Invariances be build as static functions in the structure?
yes
no
Explanation:
Invariances have to be dynamically estimated from data.
Question 6
Marks : +2 | -2
Pass Ratio : 100%
Which is the most direct application of neural networks?
vector quantization
pattern mapping
pattern classification
control applications
Explanation:
Its is the most direct and multilayer feedforward networks became popular because of this.
Question 7
Marks : +2 | -2
Pass Ratio : 100%
In feedforward network, the associations corresponding to input – output patterns are stored in?
activation state
output layer
hidden layer
none of the mentioned
Explanation:
In feedforward network, the associations corresponding to input – output patterns are stored in weights of the network.
Question 8
Marks : +2 | -2
Pass Ratio : 100%
What does the matching score at first layer in recognition hamming network is indicative of?
dissimilarity of input pattern with patterns stored
noise immunity
similarity of input pattern with patterns stored
none of the mentioned
Explanation:
Matching score is simply a indicative of similarity of input pattern with patterns stored.
Question 9
Marks : +2 | -2
Pass Ratio : 100%
The competition in upper subnet of hamming network continues till?
only one unit remains negative
all units are destroyed
output of only one unit remains positive
none of the mentioned
Explanation:
The competition in upper subnet of hamming network continues till output of only one unit remains positive.
Question 10
Marks : +2 | -2
Pass Ratio : 100%
How can optimization be applied in images?
by use of simulated annealing
by attaching a feedback network
by adding an additional hidden layer
none of the mentioned
Explanation:
Optimization be applied in images by use of simulated annealing to formulate the problem as energy minimization problem.