Question 1
Approximately how much times the boltzman learning get speeded up using mean field approximation?
A. 05-Oct
B. Oct-30
C. 30-50
D. 50-70
View Answer
Answer: Option B
Explanation:
Boltzman learning get speeded up 10-30 using mean field approximation.
Question 2
Boltzman learning is a?
A. fast process
B. steady process
C. slow process
D. none of the mentioned
View Answer
Answer: Option D
Explanation:
Boltzman learning is a slow process.
Answer: Option D
Explanation:
Boltzman learning is a slow process.
Question 3
By using which method, boltzman machine reduces effect of additional stable states?
A. no such method exist
B. simulated annealing
C. hopfield reduction
D. none of the mentioned
View Answer
Answer: Option B
Explanation:
boltzman machine uses simulated annealing to reduce the effect of additional stable states.
Answer: Option B
Explanation:
boltzman machine uses simulated annealing to reduce the effect of additional stable states.
Question 4
False minima can be reduced by deterministic updates?
A. yes
B. no
View Answer
Answer: Option B
Explanation:
Presence of false minima can be reduced by stochastic update.
Answer: Option B
Explanation:
Presence of false minima can be reduced by stochastic update.
Question 5
For practical implementation what type of approximation is used on boltzman law?
A. max field approximation
B. min field approximation
C. hopfield approximation
D. none of the mentioned
View Answer
Answer: Option D
Explanation:
For practical implementation mean field approximation is used.
Answer: Option D
Explanation:
For practical implementation mean field approximation is used.
Question 6
For what purpose Feedback neural networks are primarily used?
A. classification
B. feature mapping
C. pattern mapping
D. none of the mentioned
View Answer
Answer: Option D
Explanation:
Feedback neural networks are primarily used for pattern storage.
Answer: Option D
Explanation:
Feedback neural networks are primarily used for pattern storage.
Question 7
For what purpose is pattern environment useful?
A. determining structure
B. determining desired outputs
C. determining future inputs
D. none of the mentioned
View Answer
Answer: Option D
Explanation:
Pattern environment is useful for determining weights.
Answer: Option D
Explanation:
Pattern environment is useful for determining weights.
Question 8
For which other task can boltzman machine be used?
A. pattern mapping
B. feature mapping
C. classification
D. pattern association
View Answer
Answer: Option D
Explanation:
Boltzman machine can be used for pattern association.
Answer: Option D
Explanation:
Boltzman machine can be used for pattern association.
Question 9
How are energy minima related to probability of occurrence of corresponding patterns in the environment?
A. directly
B. inversely
C. directly or inversely
D. no relation
View Answer
Answer: Option A
Explanation:
Energy minima is directly related to probability of occurrence of corresponding patterns in the environment.
Answer: Option A
Explanation:
Energy minima is directly related to probability of occurrence of corresponding patterns in the environment.
Question 10
How is effect false minima reduced
A. deterministic update of weights
B. stochastic update of weights
C. deterministic or stochastic update of weights
D. none of the mentioned
View Answer
Answer: Option B
Explanation:
Presence of false minima can be reduced by stochastic update.
Answer: Option B
Explanation:
Presence of false minima can be reduced by stochastic update.
Question 11
In boltzman learning which algorithm can be used to arrive at equilibrium?
A. hopfield
B. mean field
C. hebb
D. none of the mentioned
View Answer
Answer: Option D
Explanation:
Metropolis algorithm can be used to arrive at equilibrium.
Answer: Option D
Explanation:
Metropolis algorithm can be used to arrive at equilibrium.
Question 12
Is Boltzman law practical for implementation?
A. yes
B. no
View Answer
Answer: Option B
Explanation:
Boltzman law is too slow for implementation.
Answer: Option B
Explanation:
Boltzman law is too slow for implementation.
Question 13
Is exact representation of pattern environment possible?
A. yes
B. no
View Answer
Answer: Option B
Explanation:
Exact representation of pattern environment is not possible.
Answer: Option B
Explanation:
Exact representation of pattern environment is not possible.
Question 14
Presence of false minima will have what effect on probability of error in recall?
A. directly
B. inversely
C. no effect
D. directly or inversely
View Answer
Answer: Option A
Explanation:
Presence of false minima will increase the probability of error in recall.
Answer: Option A
Explanation:
Presence of false minima will increase the probability of error in recall.
Question 15
Probability of error in recall of stored patterns can be reduced if?
A. patterns are stored appropriately
B. inputs are captured appropriately
C. weights are chosen appropriately
D. none of the mentioned
View Answer
Answer: Option C
Explanation:
Probability of error in recall of stored patterns can be reduced if weights are chosen appropriately.
Answer: Option C
Explanation:
Probability of error in recall of stored patterns can be reduced if weights are chosen appropriately.
Question 16
What consist of boltzman machine?
A. fully connected network with both hidden and visible units
B. asynchronous operation
C. stochastic update
D. all of the mentioned
View Answer
Answer: Option D
Explanation:
Boltzman machine consist of fully connected network with both hidden and visible units operating asynchronously with stochastic update.
Answer: Option D
Explanation:
Boltzman machine consist of fully connected network with both hidden and visible units operating asynchronously with stochastic update.
Question 17
What happens when we use mean field approximation with boltzman learning?
A. it slows down
B. it get speeded up
C. nothing happens
D. may speedup or speed down
View Answer
Answer: Option B
Explanation:
Boltzman learning get speeded up using mean field approximation.
Answer: Option B
Explanation:
Boltzman learning get speeded up using mean field approximation.
Question 18
What is pattern environment?
A. probability of desired patterns
B. probability of given patterns
C. behaviour of system
D. none of the mentioned
View Answer
Answer: Option D
Explanation:
Pattern environment is probability distribution of given patterns.
Answer: Option D
Explanation:
Pattern environment is probability distribution of given patterns.
Question 19
What may be the reasons for non zero probability of error in recalling?
A. spurious stable states
B. approximation in pattern environment representation
C. extra stable states
D. all of the mentioned
View Answer
Answer: Option D
Explanation:
These all are the primary reasons for existence of non zero probability of error.
Answer: Option D
Explanation:
These all are the primary reasons for existence of non zero probability of error.
Question 20
Approximately how much times the boltzman learning get speeded up using mean field approximation?
A. 5-10
B. 10-30
C. 30-50
D. 50-70
View Answer
Answer: Option B
Explanation:
Boltzman learning get speeded up 10-30 using mean field approximation.