Confuse Skull: Deep Learning MCQ's

Deep Learning MCQ's

1. Data Collected from Survey results is an example of ______

structured data

2. Gradient at a given layer is the product of all gradients at the previous layers.

True

3. Name the component of a Neural Network where the true value of the input is not observed.

hidden layer

4. _______________ is a Neural Nets way of classifying inputs.

FP

5. Prediction Accuracy of a Neural Network depends on _ and .

weight and bias

6. Recurrent Networks work best for Speech Recognition.

True

7. In a Neural Network, all the edges and nodes have the same Weight and Bias values.

False

8. Recurrent Neural Networks are best suited for Text Processing.

True

9. Neural Networks Algorithms are inspired from the structure and functioning of the Human Biological Neuron.

True

10. The rate at which cost changes with respect to weight or bias is called _________

gradient

11. GPU stands for ________

graphic

12. What is the difference between the actual output and generated output known as?

cost

13. A Shallow Neural Network has only one hidden layer between Input and Output layers.

True

14. _____________ is a recommended Model for Pattern Recognition in Unlabeled Data.

auto

15. Process of improving the accuracy of a Neural Network is called _______________.

training

16. Restricted Boltzmann Machine expect the data to be labeled for Training.

False

17. What is the best Neural Network Model for Temporal Data?

recurrent

18. How do RNTS interpret words?

vector

19. Recurrent Network can input Sequence of Data Points and Produce a Sequence of Output.

True

20. A Deep Belief Network is a stack of Restricted Boltzmann Machines.

True

21.

hidden

22. All the Visible Layers in a Restricted Boltzmannn Machine are connected to each other.

False

23. What is the best Neural Network Model for Temporal Data?

recuurent

24. What are the two layers of a Restricted Boltzmann Machine called?

hidden

25. RELU stands for ________

rectified linear

26. All the Visible Layers in a Restricted Boltzmannn Machine are connected to each other.

False

27. Why is the Pooling Layer used in a Convolution Neural Network?

dimension

28. All the Visible Layers in a Restricted Boltzmannn Machine are connected to each other.

False

29. What does LSTM stand for?

long short term mem

30. All the neurons in a convolution layer have different Weights and Biases.

False

31. The measure of Difference between two probability distributions is know as

KL Diver

32. ___________ works best for Image Data.

convultion

33. Neural Networks Algorithms are inspired from the structure and functioning of the Human Biological Neuron.

True

34. Autoencoders cannot be used for Dimensionality Reduction.

False

35. What is the method to overcome the Decay of Information through time in RNN known as?

Gating

36. De-noising and Contractive are examples of _____________

autoencoder

37. What is the difference between the actual output and generated output known as?

cost

38. ________________ models are best suited for Recursive Data.

Recursive neutral tensor nets

39. A _______________ matches or surpases the output of an individual neuron to a visual stimuli.

Convolution

40. Support Vector Machines, Naive Bayes and Logistic Regression are used for solving ___________________ problems

Classification

41. How do RNTS interpret words?

Vector Representations

No comments:

Post a Comment