1. Name the component of a Neural Network where the true value of the input is not observed.
Hidden layer
2. Data Collected from Survey results is an example of
Structured data
3. A Shallow Neural Network has only one hidden layer between Input and Output layers.
True
4. The rate at which cost changes with respect to weight or bias is called __________________.
Gradient
5. Neural Networks Algorithms are inspired from the structure and functioning of the Human Biological
Neuron.
True
6. Gradient at a given layer is the product of all gradients at the previous layers.
true
7. _______________ is a recommended Model for Pattern Recognition in Unlabeled Data.
AutoEncoders
8. Process of improving the accuracy of a Neural Network is called _______________.
training
9. What is the difference between the actual output and generated output known as?
Cost
10. Data Collected from Survey results is an example of ___________________.
Structured data
11. ________________ works best for Image Data
Con.. network
12. Support Vector Machines, Naive Bayes and Logistic Regression are used for solving
___________________ problems.
Clasification
13. In a Neural Network, all the edges and nodes have the same Weight and Bias values.
false
14. _____________________ is a Neural Nets way of classifying inputs.
Forward propagation
15. Recurrent Networks work best for Speech Recognition.
True
16. Recurrent Neural Networks are best suited for Text Processing.
True
17. Prediction Accuracy of a Neural Network depends on _______________ and ______________.
Weight and bias
18. What is the best Neural Network Model for Temporal Data?
RNN
19. All the neurons in a convolution layer have different Weights and Biases.
False
20. Restricted Boltzmann Machine expects the data to be labeled for Training.
False
21. A Deep Belief Network is a stack of Restricted Boltzmann Machines.
True
22. Why is the Pooling Layer used in a Convolution Neural Network?
Dimension Reduction
23. What are the two layers of a Restricted Boltzmann Machine called?
Hidden and visible
24. The measure of Difference between two probability distributions is known as
________________________.
KL
25. A _________________ matches or surpass the output of an individual neuron to visual stimuli.
Convolution
26. All the Visible Layers in a Restricted Boltzmannn Machine are connected to each other.
False
27. What is the method to overcome the Decay of Information through time in RNN known as?
Gating
28. RELU stands for ______________________________.
Rectified Linear
29. Recurrent Network can input Sequence of Data Points and Produce a Sequence of Output.
True
30. De-noising and Contractive are examples of __________________.
Shallow - wrong
How do RNTS interpret words?
Word – wrong
Autoencoders are trained using _____________________.
back
