Deep Learning

1.In a Neural Network, all the edges and nodes have the same Weight and Bias
values.
->F

2.Prediction Accuracy of a Neural Network depends on _______________ and

______________.
->weight and bias

3._____________________ is a Neural Nets way of classifying inputs.

Forward Propagation

4.Recurrent Networks work best for Speech Recognition.

->T

5.________________ works best for Image Data.

->Convolution n/w

6.The rate at which cost changes with respect to weight or bias is called
__________________.
->Gradient

7._______________ is a recommended Model for Pattern Recognition in Unlabeled Data.

Autoencoders

8.Support Vector Machines, Naive Bayes and Logistic Regression are used for solving
___________________ problems.
->Classification

9.A Shallow Neural Network has only one hidden layer between Input and Output
layers.
->T

10.Data Collected from Survey results is an example of ___________________.

->structured data

11.GPU stands for __________.

->Graphics Processing Unit

12.The rate at which cost changes with respect to weight or bias is called
__________________.
->Gradient

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

->Training

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

->Dimension reduction

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

________________________.
->KL divergence

16.All the neurons in a convolution layer have different Weights and Biases.
->F

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

->T
18.What does LSTM stand for?
->Long-short term memory

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

Recurrent Neural Network

20.A _________________ matches or surpases the output of an individual neuron to a

visual stimuli.
->Convolution

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

->Hidden and Visible Layers

22.1. All the Visible Layers in a Restricted Boltzmannn Machine are connected to
each other.
->F

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

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

What is the difference between the actual output and generated output known as
Cost

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

Recurrent Neural Networks are best suited for Text Processing

T

Restricted Boltzmann Machine expects the data to be labeled for Training

F

What is the method to overcome the Decay of Information through time in RNN known
as
Gating

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

RELU stands for ______________________________

Rectified Linear Unit

All the Visible Layers in a Restricted Boltzmann Machine are connected to each
other
F

Autoencoders cannot be used for Dimensionality Reduction.

F