Soft Computing FT3

1. How are input layer units connected to second layer in competitive learning networks?

A) feedforward and feedback
B) feedforward or feedback
C) feedback manner
D) feedforward manner

2. Which layer has feedback weights in competitive neural networks?

A) hidden layer
B) input layer
C) output layer
D) second layer

3. What is an instar?

A) may receive or give input or output to others
B) receives inputs from all others
C) gives output to all others

4. Which type of learning is involved in ART?

A) UnSupervised
B) Supervised
C) Supervised and Unsupervised

5. What does ART stand for?

A) Adaptive Resonance Theory
B) Artificial Resonance Theory
C) Automatic Resonance Theory

6. What type of inputs does ART 1 receives?

A) Bipolar
B) Binary and Bipolar
C) Binary

7. . A greater value of p the vigilance parameter leads to?

A) No change
B) Large Cluster
C) Small cluster

8. What consist of a basic counterpropagation network?

A) feed forward network only
B) feedforwward network with hidden layer
C) two feedforward network with hidden layer

9. . How does the name counterpropagation signifies its architecture?

A) its ability to learn forward and inverse mapping functions
B) its ability to learn forward mapping functions
C) its ability to learn inverse mapping functions

10. In self organizing network, how is layer connected to output layer?

A) all are one to one connected
B) each input unit is connected to each output unit
C) some are connected

11. What kind of learning is involved in pattern clustering task?

A) UnSupervised
B) Learning with critic
C) Supervised

12. Learning Vector Quantization is a competitive network which uses supervised learning.

A) FALSE
B) TRUE

13. Negative sign of weight indicates?

A) excitatory input
B) inhibitory inpur

14. In what ways can output be determined from activation value?

A) deterministically
B) both deterministically & stochastically
C) stochastically

15. What does the activation value of winner unit is indicative of?

A) greater the degradation more is the activation value of winning units
B) greater the degradation less is the activation value of winning units
C) greater the degradation less is the activation value of other units

16. In pattern clustering, does physical location of a unit relative to other unit has any significance?

A) No
B) depends on type of clustering
C) Yes

17. What is competitive learning?

A) learning laws which modulate difference between synaptic weight & activation value
B) learning laws which modulate difference between synaptic weight & output signal
C) learning laws which modulate difference between actual output & desired output

18. The number of units in hidden layers depends on?

A) the overall characteristics of the mapping problem
B) the number of outputs
C) the number of inputs

19. What is capacity of a network?

A) the number of inputs it can deliver
B) the number of inputs it can take
C) the number of patterns that can be stored

20. Learning is a?

A) can be slow or fast in general
B) Fast process
C) Slow process

Created with That Quiz — where test making and test taking are made easy for math and other subject areas.