Deep Learning MCQ (Quiz), W3Schools : Free Time Learning

1 .

When did deep learning start?

A)

1943

B)

1962

C)

1978

D)

1989

Correct Answer : 1943

Explanation : The history of deep learning dates back to 1943 when Warren McCulloch and Walter Pitts created a computer model based on the neural networks of the human brain.

2 .

Who is father of deep learning?

A)

Ilya Sutskever

B)

David Rumelhart

C)

Alex Krizhevsky

D)

Frank Rosenblatt

Correct Answer : Frank Rosenblatt

Explanation : We conclude that Frank Rosenblatt developed and explored all the basic ingredients of the deep learning systems of today, and that he should be recognized as a Father of Deep Learning, perhaps together with Hinton, LeCun and Bengio who have just received the Turing Award as the fathers of the deep learning revolution.

3 .

How many layers Deep learning algorithms are constructed?

A)

2

B)

3

C)

4

D)

5

Correct Answer : 3

Explanation : Deep learning algorithms are constructed with 3 connected layers :
* inner layer
* outer layer
* hidden layer

4 .

Which of the following is a subset of machine learning?

A)

SciPy

B)

Numpy

C)

Deep learning

D)

All of the above

Correct Answer : Deep learning

Explanation : Deep learning is a computer software that mimics the network of neurons in a brain. It is a subset of machine learning and is called deep learning.

5 .

The Deep Learning first layer is called the?

A)

hidden layer

B)

outer layer

C)

inner layer

D)

None of the above

Correct Answer : inner layer

Explanation : The first layer is called the Input Layer. The last layer is called the Output Layer. All layers in between are called Hidden Layers.

6 .

Assume that your machine has a large enough RAM dedicated to training neural networks. Compared to using stochastic gradient descent for your optimization, choosing a batch size that fits your RAM will lead to::

A)

a more precise but slower update.

B)

a less precise but faster update.

C)

a less precise and slower update.

D)

a more precise and faster update.

Correct Answer : a more precise but slower update.

7 .

Which of the following methods DOES NOT prevent a model from overfitting to the training set?

A)

Dropout

B)

Pooling

C)

Early stopping

D)

Data augmentation

Correct Answer : Pooling

8 .

In which of the following applications can we use deep learning to solve the problem?

A)

Protein structure prediction

B)

Detection of exotic particles

C)

Prediction of chemical reactions

D)

All of the above

Correct Answer : All of the above

Explanation : We can use neural network to approximate any function so it can theoretically be used to solve any problem.

9 .

Which of the following statements is true when you use 1×1 convolutions in a CNN?

A)

It can be used for feature pooling

B)

It can help in dimensionality reduction

C)

It suffers less overfitting due to small kernel size

D)

All of the above

Correct Answer : All of the above

Explanation : 1×1 convolutions are called bottleneck structure in CNN.

10 .

RNNs stands for?

A)

Recurrent Neural Networks

B)

Report Neural Networks

C)

Receives Neural Networks

D)

Recording Neural Networks

Correct Answer : Recurrent neural networks

Explanation : Recurrent neural networks (RNNs) : RNN is a multi-layered neural network that can store information in context nodes, allowing it to learn data sequences and output a number or another sequence.

11 .

Which of the following is well suited for perceptual tasks?

A)

Reinforcement Learning

B)

Recurrent Neural Networks

C)

Convolutional Neural Networks

D)

Feed-forward Neural Networks

Correct Answer : Convolutional Neural Networks

Explanation : Convolutional Neural Networks(CNN) is a multi-layered neural network with a unique architecture designed to extract increasingly complex features of the data at each layer to determine the output. CNNs are well suited for perceptual tasks.

12 .

CNN is mostly used when there is an?

A)

structured data

B)

unstructured data

C)

Both A and B

D)

None of the above

Correct Answer : unstructured data

Explanation : CNN is mostly used when there is an unstructured data set (e.g., images) and the practitioners need to extract information from it.

13 .

Which neural network has only one hidden layer between the input and output?

A)

Deep neural network

B)

Shallow neural network

C)

Recurrent neural networks

D)

Feed-forward neural networks

Correct Answer : Shallow neural network

Explanation : Shallow neural network : The Shallow neural network has only one hidden layer between the input and output.

14 .

The number of nodes in the input layer is 10 and the hidden layer is 5. The maximum number of connections from the input layer to the hidden layer are :

A)

50

B)

Less than 50

C)

More than 50

D)

It is an arbitrary value

Correct Answer : 50

Explanation : Since MLP is a fully connected directed graph, the number of connections are a multiple of number of nodes in input layer and hidden layer.

15 .

The input image has been converted into a matrix of size 28 X 28 and a kernel/filter of size 7 X 7 with a stride of 1. What will be the size of the convoluted matrix?

A)

20x20

B)

21x21

C)

22x22

D)

25x25

Correct Answer : 22x22

Explanation : The size of the convoluted matrix is given by C=((I-F+2P)/S)+1, where C is the size of the Convoluted matrix, I is the size of the input matrix, F the size of the filter matrix and P the padding applied to the input matrix. Here P=0, I=28, F=7 and S=1. There the answer is 22.

16 .

What consist of Boltzmann machine?

A)

stochastic update

B)

asynchronous operation

C)

fully connected network with both hidden and visible units

D)

All of the Above

Correct Answer : All of the Above

17 .

Which, if any, of the following propositions is true about fully-connected neural networks (FCNN)?

A)

In a FCNN, there are connections between neurons of a same layer.

B)

A FCNN with only linear activations is a linear network.

C)

In a FCNN, the most common weight initialization scheme is the zero initialization, because it leads to faster and more robust training.

D)

None of the above

Correct Answer : None of the above

18 .

In a simple MLP model with 8 neurons in the input layer, 5 neurons in the hidden layer and 1 neuron in the output layer. What is the size of the weight matrices between hidden output layer and input hidden layer?

A)

[1 X 5] , [5 X 8]

B)

[5 x 1] , [8 X 5]

C)

[8 X 5] , [5 X 1]

D)

[8 X 5] , [ 1 X 5]

Correct Answer : [5 x 1] , [8 X 5]

Explanation : The size of weights between any layer 1 and layer 2 Is given by [nodes in layer 1 X nodes in layer 2].

19 .

Which of the following is/are Common uses of RNNs?

A)

Provide a caption for images

B)

Detect fraudulent credit-card transaction

C)

BusinessesHelp securities traders to generate analytic reports

D)

All of the Above

Correct Answer : All of the Above

Explanation : All of the above are Common uses of RNNs.

20 .

Which of the following is/are Limitations of Deep Learning?

A)

Data Labeling

B)

Obtain Huge Training Datasets

C)

Both A and B

D)

None of the above

Correct Answer : Both A and B

Explanation : Both A and B are Limitations of Deep Learning.

21 .

Deep Learning algorithms are _______ more accurate than machine learning algorithm in image classification.

A)

41%

B)

37%

C)

31%

D)

28%

Correct Answer : 41%

Explanation : Deep Learning can outperform traditional method. For instance, deep learning algorithms are 41% more accurate than machine learning algorithm in image classification, 27% more accurate in facial recognition and 25% in voice recognition.

22 .

Which of the following would have a constant input in each epoch of training a Deep Learning model?

A)

Weight between input and hidden layer

B)

Weight between hidden and output layer

C)

Activation function of output layer

D)

Biases of all hidden layer neurons

Correct Answer : Weight between input and hidden layer

Explanation : Weights between input and hidden layer are constant.

23 .

Which of the following functions can be used as an activation function in the output layer if we wish to predict the probabilities of n classes (p1, p2..pk) such that sum of p over all n equals to 1?

A)

Tanh

B)

Softmax

C)

ReLu

D)

Sigmoid

Correct Answer : Softmax

Explanation : Softmax function is of the form in which the sum of probabilities over all k sum to 1.

24 .

In CNN, having max pooling always decrease the parameters?

A)

True

B)

False

C)

--

D)

--

Correct Answer : False

Explanation : This is not always true. If we have a max pooling layer of pooling size as 1, the parameters would remain the same.

25 .

Sentiment analysis using Deep Learning is a many-to one prediction task

A)

True

B)

False

C)

--

D)

--

Correct Answer : True

Explanation : Option A is correct. This is because from a sequence of words, you have to predict whether the sentiment was positive or negative.

26 .

Assume a simple MLP model with 3 neurons and inputs= 1,2,3. The weights to the input neurons are 4,5 and 6 respectively. Assume the activation function is a linear constant value of 3. What will be the output ?

A)

128

B)

64

C)

256

D)

96

Correct Answer : 96

Explanation : The output will be calculated as 3(1*4+2*5+6*3) = 96

27 .

What is a Boltzman machine?

A)

A feedback network with hidden units

B)

A feed forward network with hidden units

C)

A feedback network with hidden units and probabilistic update

D)

A feed forward network with hidden units and probabilistic update

Correct Answer : A feedback network with hidden units and probabilistic update

Explanation : Boltzman machine is a feedback network with hidden units and probabilistic update.

Deep Learning - MCQ(Quiz)