Machine Learning

Question 1

Which of the following are the advantages of transformers over a recurrent sequence model?
a) better at learning long-range dependencies
b) Slower to train and run-on modern hardware
c) require many fewer parameters to achieve similar results
d) none of the above

Answer 1

a) better at learning long-range dependencies

Question 2

Which of these parts of the self-attention operation are calculated by passing inputs through MLP?
a) values
b) keys
c) queries
d) all the above

Answer 2

d) all the above

Question 3

What is the field of natural language processing (NLP)?
a) computer science
b) artificial intelligence
c) linguistics
d) all of the mentioned

Answer 3

d) all of the mentioned

Question 4

What is the main challenge/s of NLP?
a) handling ambiguity of sentences
b) handling tokenization
c) handling pos-tagging
d) All of the mentioned

Answer 4

a) handling ambiguity of sentences

Question 5

What is machine translation?
a) Converts one human language to another
b) Converts human language to machine language
c) Converts any human language to English
d) Converts machine language to human language

Answer 5

a) Converts one human language to another

Question 6

choose from the following areas where NLP can be useful.
a) automatic text summarization
b) automatic question-answering systems
c) information retrieval
d) all the mentioned

Answer 6

d) all the mentioned

Question 7

Which of the following properties will a good position encoding ideally have?
a) unique for all positions
b) relative distances are independent of absolute sequence position
c) well-defined for arbitrary sequence lengths
d) all the above

Answer 7

d) all the above

Question 8

Which of the following includes the major tasks of NLP?
a) automatic summarization
b) discourse analysis
c) machine translation
d) all the mentioned

Answer 8

d) all the mentioned

Question 9

Neural machine translation was based on encoder-decoder _____
a) RNNs
b) LSTMs
c) both a & b
d) neither a & b

Answer 9

c) both a & b

Question 10

The encoder LSTM is used to process the _____ sentence.
a) input
b) output
c) function
d) All the above

Answer 10

a) input

Question 11

What is the type of autoencoder?
a) Supervised neural network
b) unsupervised neural network
c) semi-supervised neural network
d) reinforcement neural network

Answer 11

b) unsupervised neural network

Question 12

What type of data can the autoencoder apply dimensionality reduction on?
a) linear data
b) nonlinear data
c) both a & b
d) none of the above

Answer 12

c) both a & b

Question 13

A module that compresses data into an encoded representation that is typically several orders of magnitude smaller than the input data.
a) The encoder
b) Bottleneck
c) The decoder
d) None of the above

Answer 13

a) The encoder

Question 14

a module that contains the compressed knowledge representation and considers the most important part of the autoencoder network?
a) the encoder
b) bottleneck
c) the decoder
d) None of the above

Answer 14

b) bottleneck

Question 15

A module that helps the network “decompress” the knowledge representations and reconstructs the data back from its encoded form.
a) input layer
b) bottleneck
c) output layer
d) none of the above

Answer 15

c) output layer

Question 16

What type of autoencoders work by penalizing the activation of some
neurons in hidden layers?
a) Sparse autoencoder
b) Variational autoencoder
c) Deep autoencoder
d) Convolution autoencoders

Answer 16

a) Sparse autoencoder

Question 17

Which of the following is done by a deep autoencoder?
a) image reconstruction
b) image colorization
c) image search
d) image denoising

Answer 17

c) image search

Question 18

Which of the following is done by a convolution autoencoder?
a) data compression
b) image search
c) information retrieval
d) image colorization

Answer 18

d) image colorization

Question 19

Which of the following is an autoencoder application?
a) watermark removing
b) dimensionality reduction
c) image generation
d) all the above

Answer 19

d) all the above

Question 20

Which autoencoder doesn’t require reducing the bottleneck nodes?
a) sparse autoencoder
b) deep autoencoder
c) variational autoencoder
d) None of the above

Answer 20

a) sparse autoencoder

Question 21

in NLP, bidirectional context is supported by which of the following embedding
a) WORD2VEC
b) BERT
c) GLOVE
d) All the above

Answer 21

b) BERT

Question 22

For a given token, its input representation is the sum of embedding from the token, segment, and position
a) ELMO
b) GPT
c) BERT
d) none of the above

Answer 22

c) BERT

Question 23

BERT Base Contains _____ encoder layers
a) 12
b) 24
c) 36
d) 48

Answer 23

a) 12

Question 24

BERT large Contains _____ encoder layers
a) 12
b) 24
c) 36
d) 48

Answer 24

b) 24

Question 25

BERT aims at tackling various NLP tasks such as _____
a) question answering
b) language inference
c) text summarization
d) all of the mentioned

Answer 25

d) all of the mentioned

Question 26

The BERT model is pre-trained on relatively generic tasks
a) masked language modeling (MLM)
b) next sentence prediction
c) a and b
d) none of the mentioned

Answer 26

c) a and b

Question 27

_______ Is to hide a word in a sentence and then have the program predict what
word has been hidden (masked) based on the hidden word’s context.
a) Masked language modeling (MLM)
b) Next sentence prediction
c) Sequence classification
d) Named entity recognition (NER)

Answer 27

a) Masked language modeling (MLM)

Question 28

_______ is to have the program predict whether two given sentences have a
logical, sequential connection or whether their relationship is simply random
a) Masked language modeling (MLM)
b) Next sentence prediction
c) Sequence classification
d) Named entity recognition (NER)

Answer 28

b) Next sentence prediction

Question 29

BERT Can process text ______
a) left-to-right
b) right-to-left
c) both
d) none of the mention

Answer 29

c) both

Question 30

BERT was created and published in 2018 By ______
a) Amazon
b) Microsoft
c) IBM
d) Google

Answer 30

d) Google

Question 31

What is the difference between CNN and ANN?
a) CNN has one or more layers of convolution units, which receive its input from multiple units.
b) CNN uses a simpler algorithm than ann.
c) They complete each other, so to use ANN, you need to start with CNN.
d) CNN is the easiest way to use neural networks.

Answer 31

a) CNN has one or more layers of convolution units, which receive its input from multiple units.

Question 32

The data fed into the model and output from each layer is obtained. this step is called.
a) Feed forward
b) Feed backward
c) Input layer
d) Output layer

Answer 32

a) Feed forward

Question 33

Common types of pooling layers.
a) 5
b) 2
c) 3
d) 4

Answer 33

b) 2

Question 34

computes the output volume by the computing dot product between all filters and image patches.
a) Input layer
b) Convolution layer
c) Activation function layer
d) Pool layer

Answer 34

b) Convolution layer

Question 35

What is back propagation?
a) it is another name given to the curvy function in the perceptron
b) it is the transmission of error back through the network to adjust the inputs
c) it is the transmission of error back through the network to allow weights to be adjusted so that the network can learn
d) all of the mentioned

Answer 35

c) it is the transmission of error back through the network to allow weights to be adjusted so that the network can learn

Question 36

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 the sum of p over all n equals 1?
a) RELU
b) Sigmoid
c) Softmax
d) Tanh

Answer 36

c) Softmax

Question 37

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) Biases of all hidden layer neurons
d) Activation function of output layer

Answer 37

a) Weight between input and hidden layer

Question 38

Which of the following neural network training challenges can be solved using
batch normalization?
a) overfitting
b) underfitting
c) training is too slow
d) none of the mentioned

Answer 38

c) training is too slow

Question 39

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) None of the mentioned

Answer 39

a) 50

Question 40

Is Deep Learning a specialized subset of machine learning?
a) true
b) false

Answer 40

a) true

Question 41

_____ are models, used to generate data similar to the data on which they are trained, by destroying training data through the successive addition of gaussian noise, and then learning to recover the data by reversing this noising process.
a) Federal learning.
b) Attention learning.
c) CNN.
d) Diffusion models.

Answer 41

d) Diffusion models.

Question 42

What is the goal of training a diffusion model?
a) Learn the reverse process
b) Learn to understand the image
c) Extract the image features
d) Classify the images

Answer 42

a) Learn the reverse process

Question 43

one of the benefits of the diffusion model is _____
a) scalability
b) not requiring adversarial training.
c) parallelizability
d) all of the above.

Answer 43

d) all of the above.

Question 44

in general diffusion model consist of _____ main process
a) 5
b)4
c) 3
d)2

Answer 44

d)2

Question 45

A diffusion model is trained by finding the reverse Markov transitions that the likelihood of the training data.
a) Maximize
b) Minimize.
c) Increase.
d) Decrease.

Answer 45

a) Maximize

Question 46

for the reverse process in the diffusion model, we much choose the _____
a) the Sobel filter
b) Laplacian operator
c)thresholding method
d)the gaussian distribution parameterization

Answer 46

d)the gaussian distribution parameterization

Question 47

the transition distributions in the Markov chain are gaussian, where the forward process requires a ______, and the reverse process parameters are learned.
a) variance schedule
b) Laplacian operator.
c)the gaussian distribution parameterization.
d)none of the mentioned.

Answer 47

d)none of the mentioned.

Question 48

our diffusion model is parameterized as a Markov chain, meaning that our latent variables depend only on the _____ timestep
a) previous or following
b) previous
c) following
d) none of the mentioned

Answer 48

a) previous or following

Question 49

a _____ is used to obtain log-likelihoods across pixel values as the last step in the reverse diffusion process.
a) kl divergences
b) simplified training objective
c) u-net-like.
d) discrete decoder.

Answer 49

d) discrete decoder.

Question 50

diffusion models can be applied to
a) image denoising
b) super-resolution.
c) image generation.
d) all of the above.

Answer 50

d) all of the above.

Question 51

What is the main goal of federated learning?
a) to train a single machine learning model on a centralized dataset
b) to train multiple machine learning models on decentralized datasets
c) to train a single machine learning model on decentralized datasets
d) to train multiple machine learning models on a centralized dataset

Answer 51

c) to train a single machine learning model on decentralized datasets

Question 52

How does federated learning differ from traditional machine learning?
a) federated learning requires less data
b) federated learning requires more computational resources
c) federated learning requires less communication bandwidth
d) federated learning requires more data privacy concerns

Answer 52

d) federated learning requires more data privacy concerns

Question 53

What is an advantage of federated learning compared to traditional centralized training?
a) it is more accurate
b) it is faster
c) it requires less data
d) it allows for decentralized data to be used

Answer 53

d) it allows for decentralized data to be used

Question 54

How is data privacy protected in federated learning?
a) data is encrypted before being sent to the centralized server
b) data is never shared with any other parties
c) data remains on the individual devices and is only used for model training
d) data is aggregated and anonym zed before being used for model training

Answer 54

c) data remains on the individual devices and is only used for model training

Question 55

In federated learning, who is responsible for training the model?
a) a centralized server
b) a third-party organization
c) individual clients
d) the data owner

Answer 55

c) individual clients

Question 56

key benefits of federated learning…….
a) it involves more diverse data.
b) it’s secure.
c) it yields real-time predictions.
d) all of the above

Answer 56

d) all of the above

Question 57

What are the challenges of federated learning?
a) efficient communication across the federated network.
b) managing heterogeneous systems in the same networks.
c) privacy concerns and privacy-preserving methods.
d) all of the above

Answer 57

d) all of the above

Question 58

How does federated learning work?
a) Transfer of weights and biases to cloud server
b) Transfer of data to cloud server
c) Transfer of model to cloud server
d) Transfer of user info to cloud

Answer 58

a) Transfer of weights and biases to cloud server

Question 59

Is federated learning more efficient than standard ml techniques for a large number of devices?
a) True
b) False
c) Depends on use case
d) Cannot say

Answer 59

a) True

Question 60

federated learning is ______
a) Supervised
b) Unsupervised
c) Reinforcement learning.
d) None of the above

Answer 60

b) Unsupervised

Question 61

What is the basic concept of recurrent neural network?
a) use a loop between inputs and outputs in order to achieve the better prediction.
b) use recurrent features from dataset to find the best answers.
c) use previous inputs to find the next output according to the training set.
d) use loops between the most important features to predict next output.

Answer 61

c) use previous inputs to find the next output according to the training set.

Question 62

The other RNN´s issue is called ‘vanishing gradients’. what is that?
a) when the values of a gradient are too small and the model joins in a loop because of that.
b) when the values of a gradient are too big and the model stops learning or takes way too long because of that.
c) when the values of a gradient are too small and the model stops learning or takes way too long because of that.
d) when the values of a gradient are too big and the model joins in a loop because of that.

Answer 62

c) when the values of a gradient are too small and the model stops learning or takes way too long because of that.

Question 63

LSTM. What is that?
a) LSTM networks are an extension for recurrent neural networks, which basically extends their memory. therefore, it is well suited to learn from important experiences that have very low time lags in between
b) LSTM networks are an extension for recurrent neural networks, which basically extends their memory. therefore, it is not recommended to use it, unless you are using a small dataset.
c) LSTM networks are an extension for recurrent neural networks, which basically extends their memory. therefore, it is well suited to learn from important experiences that have long-time lags in between
d) LSTM networks are an extension for recurrent neural networks, which basically shorten their memory. therefore, it is well suited to learn from important experiences that have very low time lags in between

Answer 63

c) LSTM networks are an extension for recurrent neural networks, which basically extends their memory. therefore, it is well suited to learn from important experiences that have long-time lags in between

Question 64

The network that involves backward links from output to the input and hidden layers is called _________
a) self-organizing maps
b) perceptron
c) recurrent neural network
d) multi layered perceptron

Answer 64

c) recurrent neural network

Question 65

RNNs Stands for?
a) Recurrent neural networks
b) Report neural networks
c) Receives neural networks
d) Recording neural networks

Answer 65

a) Recurrent neural networks

Question 66

What is the activation function used in forget gate?
a) Sigmoid
b) Tanh
c) RELU
d) None of the above

Answer 66

a) Sigmoid

Question 67

How Many Gates Are There In LSTM?
a) 3
b) 5
c) 4
d) 2

Answer 67

a) 3

Question 68

……, When the points in the dataset are dependent on the other points in the dataset.
a) continuous data
b) discrete data
c) sequential data
d) ordinal data

Answer 68

c) sequential data

Question 69

……… helps to identify important elements that need to be added to the cell state.
a) Forget gate
b) Input gate
c) Output gate
d) None of the above

Answer 69

b) Input gate

Question 70

LSTM used in ……
a) speech recognition
b) music composition
c) time series prediction
d) all of the above

Answer 70

d) all of the above

Question 71

what should be the aim of training procedure in Boltzmann machine of
feedback networks?
a) to capture inputs
b) to feedback the captured outputs
c) to capture the behavior of system
d) none of the mentioned

Answer 71

d) none of the mentioned

Question 72

What consist of Boltzmann machine?
a) fully connected network with both hidden and visible units
b) asynchronous operation
c) stochastic update
d) all of the mentioned

Answer 72

d) all of the mentioned

Question 73

by using which method, Boltzmann machine reduces the effect of additional stable states?
a) No such method exists
b) Simulated annealing
c) Hopfield reduction
d) None of the mentioned

Answer 73

b) Simulated annealing

Question 74

for which another task can Boltzmann machine be used?
a) pattern mapping
b) feature mapping
c) classification
d) pattern association

Answer 74

d) pattern association

Question 75

Presence of false minima will have what effect on probability of error in recall?
a) Directly
b) Inversely
c) No effect
d) Directly or Inversely

Answer 75

a) Directly

Question 76

What happens when we use mean field approximation with Boltzmann learning?
a) It slows down
b) It gets speeded up
c) Nothing happens
d) may speedup or speed down

Answer 76

b) It gets speeded up

Question 77

in Boltzmann learning which algorithm can be used to arrive at equilibrium?
a) Hopfield
b) mean field
c) Hebb
d) none of the mentioned

Answer 77

d) none of the mentioned

Question 78

All the visible layers in a restricted Boltzmann machine are not connected to
each other.
a) True
b) False

Answer 78

a) True

Question 79

What are the two layers of a restricted Boltzmann machine called?
a) input and output layers
b) recurrent and convolution layers
c) activation and threshold layers
d) hidden and visible layers

Answer 79

d) hidden and visible layers

Question 80

A deep belief network is a stack of restricted Boltzmann machines.
a) True
b) False

Answer 80

a) True

Question 81

the main and most important feature of RNN is _________.
a) visible state
b) hidden state
c) present state
d) None of these

Answer 81

b) hidden state

Question 81

RNN remembers each and every information through________.
a) Work
b) Time
c) Hours
d) Memory

Answer 81

b) Time

Question 82

to create a numerical representation of our text-based dataset we generate two lookup table, what are they_____.
a) maps character to numbers
b) maps numbers back to characters
c) identify unique characters present in text
d) both a & b

Answer 82

d) both a & b

Question 83

_______occurs when the gradients become very small and tend towards zero.
a) Exploding gradients
b) Vanishing gradients
c) Long short-term memory networks
d) Gated recurrent unit networks.

Answer 83

b) Vanishing gradients

Question 84

on what parameters can change in weight vector depend?
a) learning parameters
b) input vector
c) learning signal
d) all of the mentioned

Answer 84

d) all of the mentioned

Question 85

________Occurs when the gradients become too large due to back-propagation.
a) Exploding gradients
b) Vanishing gradients
c) Long short-term memory networks
d) Gated recurrent unit networks

Answer 85

a) Exploding gradients

Question 86

If a competitive network can perform feature mapping, then what is that network can be called?
a) self-excitatory
b) self-inhibitory
c) self-organization
d) none of the mentioned

Answer 86

c) self-organization

Question 87

why do we need biological neural networks?
a) to solve tasks like machine vision & natural language processing
b) to apply heuristic search methods to find solutions of problem
c) to make smart human interactive & user-friendly system
d) all of the mentioned

Answer 87

d) all of the mentioned

Question 88

what is auto-association task in neural networks?
a) find relation between 2 consecutive inputs
b) related to storage & recall task
c) predicting the future inputs
d) None of the mentioned

Answer 88

b) related to storage & recall task

Question 89

What is unsupervised learning?
a) features of group explicitly stated
b) number of groups may be known
c) neither feature & nor number of groups is known
d) none of the mentioned

Answer 89

c) neither feature & nor number of groups is known

Question 90

XLNet Is an ________ language model which outputs the joint probability of a sequence of tokens based on the transformer architecture with recurrence.
a) Auto-regressive
b) Auto-Negressive
c) Objective
d) Bidirectional

Answer 90

a) Auto-regressive

Question 91

XLNet Is “Generalized” because it captures bi-directional context by means of
a) mechanism called____
a) PLM
b) BERT
c) TRANSFORMER-XL
d) MLM

Answer 91

a) mechanism called____

Question 92

______ Keep track of the position of each token in a sequence (will know why
we have this in the later sections)
a) pretrain-finetune discrepancy
b) transformer-xl
c) positional encoding
d) segment recurrence

Answer 92

c) positional encoding

Question 93

______ cache the hidden state of first segment in memory in each layer and update attention accordingly. it allows reuse of memory for each segment.
a) pretrain-finetune discrepancy
b) transformer-xl
c) positional encoding
d) segment recurrence

Answer 93

d) segment recurrence

Question 94

the attention weights determined by a simple feed forward neural network are____
a) query
b) keys
c) values
d) all of the above

Answer 94

d) all of the above

Question 95

_____ Traditional Methods predict the current token given previous “n” tokens, or predict the current token given all tokens after it.
a) Bidirectional
b) Masked language modeling
c) XLNet
d) BERT

Answer 95

a) Bidirectional

Question 96

______Is A Neural Network architecture that can model bidirectional contexts in text data using transformer.
a) BERT
b) XLNet
c) MLM
d) PLM

Answer 96

a) BERT

Question 97

A disadvantage of BERT is it corrupts the input with _______ and suffers from pretrain-finetune discrepancy.
a) Mask
b) PLM
c) MLM
d) All of above

Answer 97

a) Mask

Question 98

XLNet Is the latest and greatest model to emerge from the booming field of natural language processing (NLP)
a) True
b) False

Answer 98

a) True

Question 99

XLNet Is “Generalized”
a) True
b) False

Answer 99

a) True

Question 100

The Attention Learning mechanism has changed the way we work with deep
learning algorithm
a) true
b) false

Answer 100

a) true

Question 101

the advantage of transformers over recurrent sequence model is slower to train and run on Modern Hardware
a) true
b) false

Answer 101

b) false

Question 102

Fields like NLP and Computer Vision have been revolutionized by the attention mechanism
a) true
b) false

Answer 102

a) true

Question 103

Attention Learning is an Interface connecting the Encoder and Decoder that provides the Decoder with Information
a) true
b) false

Answer 103

a) true

Question 104

the encoder LSTM or RNN units produce the words in a sentence one after another
a) true
b) false

Answer 104

b) false

Question 105

The Encoder reads the input sentence and tries to make sense of it
a) true
b) false

Answer 105

a) true

Question 106

The LSTM is supposed to capture the Long-Range dependency better than the RNN
a) true
b) false

Answer 106

a) true

Question 107

RNNs Can’t remember longer sentences and sequences
a) true
b) false

Answer 107

a) true

Question 108

If the Encoder makes a bad summary, the translation will be also bad
a) true
b) false

Answer 108

a) true

Question 109

the Decoder is used to process the entire input sentence and decode it into a Context Vector
a) true
b) false

Answer 109

b) false

Question 110

autoencoders belong to supervised neural networks
a) true
b) false

Answer 110

b) false

Question 111

Bottleneck Is the most important part of the network
a) true
b) false

Answer 111

a) true

Question 112

Convolution Autoencoders Can Do Image Reconstruction
a) true
b) false

Answer 112

a) true

Question 113

Deep Autoencoder is composed of two, Symmetrical Deep-Belief networks
a) true
b) false

Answer 113

a) true

Question 114

Deep Autoencoders can’t do image search
a) true
b) false

Answer 114

b) false

Question 115

Sparse Autoencoders Offer us an alternative method for introducing an
information Bottleneck without requiring a reduction in the number of nodes
a) true
b) false

Answer 115

a) true

Question 116

Sparse Autoencoders work by penalizing the activation of Neurons in input
layer
a) true
b) false

Answer 116

b) false

Question 117

Autoencoders can De-Noise images
a) true
b) false

Answer 117

a) true

Question 118

Autoencoders can’t be used to reduce dimensionality
a) true
b) false

Answer 118

b) false

Question 119

the Encoder module that helps the network “decompress” the knowledge representations and reconstructs the data back from its encoded form
a) true
b) false

Answer 119

b) false

Question 120

BERT (bidirectional encoder representation from transformers) is a recent paper published by researchers at Amazon AI Language?
a) true
b) false

Answer 120

b) false

Question 121

BERT doesn’t read the text input sequentially?
a) true
b) false

Answer 121

b) false

Question 122

BERT Allows Transform Learning on the existing pretrained models and hence can be custom trained for the specific subject.
a) true
b) false

Answer 122

a) true

Question 123

In BERT, The relationship between all words in a sentence is Modeled
Irrespective of their position.
a) true
b) false

Answer 123

a) true

Question 124

BERT uses unidirectional language model for producing word embedding.
a) true
b) false

Answer 124

b) false

Question 125

BERT is not an open-source machine learning framework for NLP?
a) true
b) false

Answer 125

b) false

Question 126

BERT not understand human language as it is spoken naturally.
a) true
b) false

Answer 126

b) false

Question 127

BERT is expected to have large impact on voice search as well as text-based search.
a) true
b) false

Answer 127

b) false

Question 128

same word can have multiple word embedding possible with BERT
a) True
b) False

Answer 128

b) False

Question 129

BERT is a deep bidirectional, supervised language representation
a) true
b) false

Answer 129

b) false

Question 130

pooling is an up-sampling operation that reduces the Dimensionality of the Feature Map.
a) true
b) false

Answer 130

b) false

Question 131

The RELU operation is applied to each Pixel and replaces all the negative Pixel values in the Feature Map with Zero
a) true
b) false

Answer 131

a) true

Question 132

Pooling Or Spatial Pooling Layers: Also Called Sub-Sampling
a) true
b) false

Answer 132

a) true

Question 133

Pooling reduces the Dimensionality of each feature map by retaining the most important information
a) true
b) false

Answer 133

a) true

Question 134

the aim of the fully connected layer is to use the low-level feature of the input mage produced by Convolutional and Pooling Layers
a) true
b) false

Answer 134

b) false

Question 135

The Hyperparameters for a Pooling Layer are Filter Size, Stride and max or average Pooling
a) true
b) false

Answer 135

a) true

Question 136

When we apply a filter of 1×1, then there is no reduction in the size of the image and hence there is no loss of information.
a) true
b) false

Answer 136

a) true

Question 137

flattening means that every Neuron in the previous layer is connected to each Neuron in the next layer
a) true
b) false

Answer 137

b) false

Question 138

RELU introduces linearity to the network, and the generated output is a
Rectified Feature Map
a) true
b) false

Answer 138

b) false

Question 139

Convolutional Layer Receives a set of Input Feature Maps (IFM) and
generates a set of Output Feature Maps (OFM).
a) true
b) false

Answer 139

a) true

Question 140

diffusion models work by destroying training data through the successive addition of Laplacian noise, and then learning to recover the data by reversing this noising process.
a) true
b) false

Answer 140

b) false

Question 141

A Discrete Decoder is used to obtain Log likelihoods across Pixel values as the last step in the Reverse Diffusion process.
a) true
b) false

Answer 141

a) true

Question 142

diffusion model is a latent variable model which maps to the latent space Sobel using a Fixed chain.
a) true
b) false

Answer 142

b) false

Question 143

The goal of training a Diffusion model is to learn the reverse process
a) true
b) false

Answer 143

a) true

Question 144

the transition distributions in the Markov chain are Gaussian, which depends only on the forward process.
a) true
b) false

Answer 144

b) false

Question 145

Diffusion model is parameterized as a Markov chain, meaning that our latent variables x1, … xt depend only on the previous (or following) timestep.
a) true
b) false

Answer 145

a) true

Question 146

for the reverse process in the Diffusion model, we much choose a variance schedule.
a) true
b) false

Answer 146

b) false

Question 147

The transition distributions in the Markov chain are Gaussian, where the forward process requires a variance schedule, and the reverse process parameters are learned.
a) true
b) false

Answer 147

a) true

Question 148

cascade Diffusion models (like Stable Diffusion) apply the Diffusion process on a smaller latent space for computational efficiency using a Variational Autoencoder for the up and down sampling.
a) true
b) false

Answer 148

b) false

Question 149

Diffusion Models can be applied to image De-Noising, Inpainting, Super Resolution, and Image Generation.
a) true
b) false

Answer 149

a) true

Question 150

Federated Learning is not used to improve the privacy and security of machine learning models.
a) true
b) false

Answer 150

b) false

Question 151

Federated Learning requires the use of a centralized server.
a) true
b) false

Answer 151

b) false

Question 152

Federated Learning can’t be used to train models on data that is distributed across multiple devices, such as Smartphones or IoT devices.
a) true
b) false

Answer 152

b) false

Question 153

Federated Learning requires the use of a centralized database.
a) true
b) false

Answer 153

b) false

Question 154

Federated Learning can’t be used to improve the privacy of machine learning models by keeping sensitive data on individual devices.
a) true
b) false

Answer 154

b) false

Question 155

Federated Learning is a Type of machine learning that allows multiple parties to train a model without sharing their data.
a) true
b) false

Answer 155

a) true

Question 156

Federated Learning requires participating devices to have high computational power.
a) true
b) false

Answer 156

b) false

Question 157

Federated Learning enables Participants to train local models cooperatively on local data without disclosing sensitive data to a central cloud server
a) true
b) false

Answer 157

a) true

Question 158

Federated Learning can’t be used to train deep learning models.
a) true
b) false

Answer 158

b) false

Question 159

Federated Learning can be used to train models on data that is distributed across multiple devices in real-time.
a) true
b) false

Answer 159

a) true

Question 160

In Sequential Data, the points in the dataset are dependent on the other points in the dataset.
a) true
b) false

Answer 160

a) true

Question 161

A Timeseries is a common example of Sequential Data, with each point
reflecting an observation at a certain point in time.
a) true
b) false

Answer 161

a) true

Question 162

the crucial element to remember about sequence models is that the data we’re working with are Independently and Identically Distributed (I.I.D.) samples.
a) true
b) false

Answer 162

b) false

Question 163

Sequence models are the machine learning models that input or output sequences of data.
a) true
b) false

Answer 163

a) true

Question 164

structured data includes text streams, audio clips, video clips and time-series data.
a) true
b) false

Answer 164

b) false

Question 165

the conventional feedforward artificial neural networks can deal with sequential data and can be trained to hold knowledge about the past.
a) true
b) false

Answer 165

b) false

Question 166

traditional RNNs are very excellent at capturing Long-Range dependencies.
a) true
b) false

Answer 166

b) false

Question 167

LSTMs Are explicitly designed to avoid the Long-Term Dependency problem.
a) true
b) false

Answer 167

a) true

Question 168

input gate controls what information should be forgotten.
a) true
b) false

Answer 168

b) false

Question 169

input gate helps to Identify important elements that need to be added to the cell state.
a) true
b) false

Answer 169

a) true

Question 170

RBMs are a supervised learning technique
a) true
b) false

Answer 170

b) false

Question 171

RBM isn’t restricted to have only the connections between the visible and the
hidden units
a) true
b) false

Answer 171

b) false

Question 172

RBM performs discriminative learning similar to what happens in a
classification problem
a) true
b) false

Answer 172

b) false

Question 173

If number of visible nodes = nV, number of hidden nodes = nH, then number of connections in RBM = nV* nH
a) true
b) false

Answer 173

a) true

Question 174

Boltzmann machines are non-deterministic generative deep learning models with 3 types of nodes: visible, hidden and output nodes
a) true
b) false

Answer 174

b) false

Question 175

Boltzmann machines Fall into the class of unsupervised learning.
a) true
b) false

Answer 175

a) true

Question 176

sparse Autoencoders introduces information Bottleneck by reducing the number of nodes at hidden layers.
a) true
b) false

Answer 176

b) false

Question 177

The idea is to Encourage network to learn an Encoding and Decoding which only relies on activating a small number of neurons.
a) true
b) false

Answer 177

a) true

Question 178

To implement Undercomplete Autoencoder, constrain the number of nodes present in hidden layer(s) of the neural network.
a) true
b) false

Answer 178

a) true

Question 179

Autoencoders are not capable of learning nonlinear manifolds (a continuous, non-intersecting surface.)
a) true
b) false

Answer 179

b) false

Question 180

A Neural Network with multiple hidden layers and Sigmoid nodes can form non-linear decision boundaries.
a) true
b) false

Answer 180

a) true

Question 181

Neural Networks compute non-convex functions of their parameters.
a) true
b) false

Answer 181

b) false

Question 182

For Logistic Regression, with parameters optimized using a Stochastic Gradient method, setting parameters to 0 is an acceptable initialization.
a) true
b) false

Answer 182

a) true

Question 183

For arbitrary Neural Networks, with weights optimized using a Stochastic Gradient method, setting weights to 0 is an acceptable initialization.
a) true
b) false

Answer 183

b) false

Question 184

Given a design matrix x ∈ r^(n×d) where d &laquo_space;n, if we project our data onto a k dimensional subspace using PCA where k equals the rank of x, we recreate a perfect representation of our data with no loss.
a) true
b) false

Answer 184

a) true

Question 185

hierarchical clustering methods require a predefined number of clusters, much like k-means.
a) true
b) false

Answer 185

b) false

Question 186

Given a predefined number of clusters k, globally minimizing the k-means objective function is NP-hard.
a) true
b) false

Answer 186

a) true

Question 187

a Random Forest is an ensemble learning method that attempts to lower the bias error of decision trees.
a) true
b) false

Answer 187

b) false

Question 188

bagging algorithms attach weights w1…wn to a set of n weak learners. they
re-weight the learners and convert them into strong ones. boosting algorithms
draw n sample distributions (usually with replacement) from an original data set
for learners to train on.
a) true
b) false

Answer 188

b) false

Question 189

using cross validation to select Hyperparameters will guarantee that our model does not overfit.
a) true
b) false

Answer 189

b) false

Question 190

Bidirectionality is Achieved by a phenomenon called “Masked Language
Modeling”.
a) true
b) false

Answer 190

a) true

Question 191

BERT Overcomes this shortcoming; in that it considers previous and next tokens to predict the current token.
a) true
b) false

Answer 191

a) true

Question 192

XLNet is not the latest and greatest model to emerge from the booming field of natural language processing (NLP).
a) true
b) false

Answer 192

b) false

Question 193

XLNet is not “generalized” because it captures Bidirectional context by means of a mechanism called “Permutation Language Modeling”.
a) true
b) false

Answer 193

b) false

Question 194

XLNet is not a generalized Autoregressive model where next token is
dependent on all previous tokens
a) true
b) false

Answer 194

b) false

Question 195

XLNet is the idea of capturing Bidirectional context by training an
Autoregressive model on all possible permutation of words in a sentence
a) true
b) false

Answer 195

b) false

Question 196

XLNet Integrates the idea of Auto-Regressive models and bi-directional context modeling, yet overcoming the disadvantages of BERT
a) true
b) false

Answer 196

a) true

Question 197

Autoregressive (AR) Language Modeling and Autoencoding (AE) have been the two most successful pretraining objectives.
a) true
b) false

Answer 197

a) true

Question 198

There are proposed methods used in XLNet like background, objective: permutation language modeling.
a) true
b) false

Answer 198

a) true

Question 199

For both BERT and XLNet, partial prediction plays a role of reducing
optimization difficulty by only predicting tokens with sufficient context.
a) true
b) false

Answer 199

a) true