Deep Learning - Chorale Prelude MCQs Solution | TCS Fresco Play | Fresco Play | TCS
Make an effort to understand these solutions and apply them to your Hands-On difficulties. (It is not advisable that copy and paste these solutions).
All Question of the MCQs Present Below for Ease Use Ctrl + F with the question name to find the Question. All the Best!
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
hidden
21. All the Visible Layers in a Restricted Boltzmann Machine are connected to each other.
FALSE
22. What is the best Neural Network Model for Temporal Data?
recuurent
23. What are the two layers of a Restricted Boltzmann Machine called?
hidden
24. RELU stands for ________
rectified linear
25. All the Visible Layers in a Restricted Boltzmann Machine are connected to each other.
FALSE
26. Why is the Pooling Layer used in a Convolution Neural Network?
dimension
27. All the Visible Layers in a Restricted Boltzmann Machine are connected to each other.
FALSE
28. What does LSTM stand for?
long short term mem
29. All the neurons in a convolution layer have different Weights and Biases.
FALSE
30. The measure of Difference between two probability distributions is know as
KL Diver
31. ___________ works best for Image Data.
convulsion
32. Neural Networks Algorithms are inspired from the structure and functioning of the Human Biological Neuron.
TRUE
33. Autoencoders cannot be used for Dimensionality Reduction.
FALSE
34. What is the method to overcome the Decay of Information through time in RNN known as?
Gating
35. De-noising and Contractive are examples of _____________
autoencoder
36. What is the difference between the actual output and generated output known as?
cost
37. ________________ models are best suited for Recursive Data.
Recursive neutral tensor nets
38. A _______________ matches or surpasses the output of an individual neuron to a visual stimuli.
Convolution
39. Support Vector Machines, Naïve Bayes and Logistic Regression are used for solving ___________________
problems Classification
40. How do RNTS interpret words?
Vector Representations
41. Autoencoders are trained using __________
feed
______________________________________
1.Gradient at a given layer is the product of all gradients at the previous layers.
True
2.Recurrent Networks work best for Speech Recognition.
True
3.Data Collected from Survey results is an example of ___________________.
Structured data
4.Neural Networks Algorithms are inspired from the structure and functioning of the Human Biological Neuron.
True
5.Name the component of a Neural Network where the true value of the input is not observed.
Hidden layer
6.Process of improving the accuracy of a Neural Network is called _______________.
Training
7.GPU Stands for
Graphics Processing Unit
8.Support Vector Machines, Naïve Bayes and Logistic Regression are used for solving ___________________ problems.
classification
9.The rate at which cost changes with respect to weight or bias is called __________________.
Gradient
10._____________________ is a Neural Nets way of classifying inputs.
Learning(*)
Classification(*)
11.What is the difference between the actual output and generated output known as?
cost
12.Prediction Accuracy of a Neural Network depends on _______________ and ______________.
weight and bias
13.________________ works best for Image Data.
Convolutional network
14.In a Neural Network, all the edges and nodes have the same Weight and Bias values.
False
15.A Shallow Neural Network has only one hidden layer between Input and Output layers.
True
16._______________ is a recommended Model for Pattern Recognition in Unlabeled Data.
Autoencoders
17.What does LSTM stand for?
Long Short Term Memory
18.A _________________ matches or surpasses the output of an individual neuron to a visual stimuli.
Convolution
19.Restricted Boltzmann Machine expects the data to be labeled for Training.
False
20.Recurrent Network can input Sequence of Data Points and Produce a Sequence of Output.
True
21.The measure of Difference between two probability distributions is know as ________________________.
KL Divergence
22.All the Visible Layers in a Restricted Boltzmann Machine are connected to each other.
False
23.RELU stands for ______________________________.
Rectified Linear Unit
24.What are the two layers of a Restricted Boltzmann Machine called?
Hidden and visible layers
25.Why is the Pooling Layer used in a Convolution Neural Network?
Dimension reduction
26.What is the best Neural Network Model for Temporal Data?
Recurrent Neural Networks
27.What is the method to overcome the Decay of Information through time in RNN known as?
Gating
28.A Deep Belief Network is a stack of Restricted Boltzmann Machines.
True
29.All the neurons in a convolution layer have different Weights and Biases.
False
30.Autoencoders are trained using _____________________.
Reconstruction(*)
Feed Forward(*)
31.Autoencoders cannot be used for Dimensionality Reduction.
False
32.________________ works best for Image Data.
Convolution Networks
33.How do RNTS interpret words?
One hot encoding(*)
34.De-noising and Contractive are examples of __________________.
Auto encoder(*)
RNN
Multi layer perceptions
35.________________ models are best suited for Recursive Data.
Recursive neural network(*)
Post a Comment