Home > Artificial Intelligence > Quizzes > Neural Network Practice Test: Feedback Neural Networks
Neural Network Practice Test: Feedback Neural Networks
Fast practice, instant feedback. Timer auto-submits when time’s up.
Avg score: 78% Most missed: “For symmetric weights there exist?”
Feedback Neural Networks topics include: Basics of feedback neural networks, pattern storage network analysis, stochastic networks, boltman machine and analysis of autoassociative neural networks. Feedback networks are also known as recurrent neural network or interactive neural network are the deep learning models in which information flows in backward direction. It allows feedback loops in the network. The feedforward neural network has an open loop but the feedback neural network has a closed loop. Input is more essential in a feedforward network system whereas the output is the most... Show more
Neural Network Practice Test: Feedback Neural Networks
Time left 00:00
25 Questions

1. Energy at each state in hopfield with symmetric weights network may increase or decrease?
2. What is a Boltzman machine?
3. Approximately how much times the boltzman learning get speeded up using mean field approximation?
4. How are energy minima related to probability of occurrence of corresponding patterns in the environment?
5. Where does a stochastic network exhibits stable states ?
6. What property should a feedback network have, to make it useful for storing information?
7. What happens when number of patterns is more than number of basins of attraction?
8. In case of deterministic update, what kind of equilibrium is reached?
9. What is the objective of pattern recall?
10. What is the objective of a pattern storage task in a network?
11. What is pattern environment?
12. What does basins of attraction corresponds to?
13. Boltzman learning is a?
14. When activation value is determined by using the average of fluctuations of outputs from other units, it is known as?
15. Linear neurons can be useful for application such as interpolation, is it true?
16. If input is ‘ a(l) + e ‘ where ‘e’ is the noise introduced, then what is the output if system is accretive in nature?
17. By using which method, boltzman machine reduces effect of additional stable states?
18. What happens when we use mean field approximation with boltzman learning?
19. What is the effect of basins of attraction on energy landscape?
20. What is hopfield model?
21. When does storage problem becomes hard problem?
22. How is effect false minima reduced
23. For what purpose is pattern environment useful?
24. Is it possible to determine exact number of basins of attraction in energy landscape?
25. Is it possible in stochastic network that average state of network doesn’t change with time?