Feedback Layer

Question 1
Marks : +2 | -2
Pass Ratio : 11%
What is the other name of feedback layer in competitive neural networks?
feedback layer
feed layer
competitive layer
no such name exist
Explanation:
Feedback layer in competitive neural networks is also known as competitive layer.
Question 2
Marks : +2 | -2
Pass Ratio : 33%
what kind of feedbacks are given in competitive layer?
self excitatory to self and others
inhibitory to self and others
self excitatory to self and inhibitory to others
inhibitory to self and excitatory to others
Explanation:
The second layer of competitive networks have self excitatory to self and inhibitory to others feedbacks to make it competitive.
Question 3
Marks : +2 | -2
Pass Ratio : 22%
How can divergence be prevented?
using hopfield criteria
sangers rule
ojas rule
sangers or ojas rule
Explanation:
Divergence can be prevented by using sangers or ojas rule.
Question 4
Marks : +2 | -2
Pass Ratio : 22%
Generally how many kinds of pattern storage network exist?
2
3
4
5
Explanation:
Namely, temporary storage, Short term memory, Long term memory.
Question 5
Marks : +2 | -2
Pass Ratio : 11%
What is ojas rule?
finds a unit weight vector
maximises the mean squared output
minimises the mean squared output
none of the mentioned
Explanation:
Ojas rule finds a unit weight vector and maximises the mean squared output.
Question 6
Marks : +2 | -2
Pass Ratio : 11%
By normalizing the weight at every stage can we prevent divergence?
yes
no
Explanation:
||w|| = 1 .
Question 7
Marks : +2 | -2
Pass Ratio : 11%
What is the nature of weights in plain hebbian learning?
convergent
divergent
may be convergent or divergent
none of the mentioned
Explanation:
In plain hebbian learning weights keep growing without bound.
Question 8
Marks : +2 | -2
Pass Ratio : 11%
An instar can respond to a set of input vectors even if its not trained to capture the behaviour of the set?
yes
no
Explanation:
An instar can respond to a set of input vectors even if it is trained to capture the average behaviour of the set.
Question 9
Marks : +2 | -2
Pass Ratio : 11%
In competitive learning, node with highest activation is the winner, is it true?
yes
no
Explanation:
This itself defines the competitive learning.
Question 10
Marks : +2 | -2
Pass Ratio : 11%
The weight change in plain hebbian learning is?
0
1
0 or 1
none of the mentioned
Explanation:
The weight change in plain hebbian learning can never be zero.