Hopfield Model-2

Question 1
Marks : +2 | -2
Pass Ratio : 100%
What is the other way to reduce error in recall due to false minima apart from stochastic update?
no other method exist
by storing desired patterns at lowest energy minima
by storing desired patterns at energy maxima
none of the mentioned
Explanation:
Error in recall due to false minima can be reduced by stochastic update or by storing desired patterns at lowest energy minima.
Question 2
Marks : +2 | -2
Pass Ratio : 100%
In hopfield network with symmetric weights, energy at each state may?
increase
decrease
decrease or remain same
decrease or increase
Explanation:
Energy of the network cant increase as it may then lead to instability.
Question 3
Marks : +2 | -2
Pass Ratio : 100%
As temperature increase, what happens to stochastic update?
increase in update
decrease in update
no change
none of the mentioned
Explanation:
Temperature doesn’t effect stochastic update.
Question 4
Marks : +2 | -2
Pass Ratio : 100%
How can error in recall due to false minima be further reduced?
using suitable activation dynamics
cannot be further reduced
by storing desired patterns at energy maxima
none of the mentioned
Explanation:
Error in recall due to false minima can further be reduced by using suitable activation dynamics.
Question 5
Marks : +2 | -2
Pass Ratio : 100%
Why does change in temperature doesn’t effect stochastic update?
shape landscape depends on the network and its weights which varies accordingly and compensates the effect
shape landscape depends on the network and its weights which is fixed
shape landscape depends on the network, its weights and the output function which varies accordingly and compensates the effect
shape landscape depends on the network, its weights and the output function which is fixed
Explanation:
Change in temperature doesn’t effect stochastic update because shape landscape depends on the network, its weights and the output function which is fixed.
Question 6
Marks : +2 | -2
Pass Ratio : 100%
Energy at each state in hopfield with symmetric weights network may increase or decrease?
yes
no
Explanation:
Energy of the network cant increase as it may then lead to instability.
Question 7
Marks : +2 | -2
Pass Ratio : 100%
Pattern storage problem which cannot be represented by a feedback network of given size can be called as?
easy problems
hard problems
no such problem exist
none of the mentioned
Explanation:
Pattern storage problem which cannot be represented by a feedback network of given size are known as hard problems.
Question 8
Marks : +2 | -2
Pass Ratio : 100%
In hopfield model with symmetric weights, network can move to?
lower
higher
lower or higher
lower or same
Explanation:
In hopfield model with symmetric weights, network can move to lower or same state.
Question 9
Marks : +2 | -2
Pass Ratio : 100%
How can error in recall due to false minima be reduced?
deterministic update for states
stochastic update for states
not possible
none of the mentioned
Explanation:
Error in recall due to false minima can be reduced by stochastic update for states.
Question 10
Marks : +2 | -2
Pass Ratio : 100%
Can error in recall due to false minima be reduced?
yes
no
Explanation:
There are generally two methods to reduce error in recall due to false minima.