Question 1

Which of the following statements about Keras neural network components is false?

Accepted Answer

A)  A neural network is a sequence of layers containing the neurons used to learn from data samples. Each layer's neurons receive inputs, process them via an optimizer function, and produce outputs. 
B)  The data is fed into the network via an input layer that specifies the dimensions of the sample data. 
C)  The input layer is followed by hidden layers of neurons that implement the learning and an output layer that produces predictions. The more layers you stack, the deeper the network is (hence the term deep learning). 
A)  A neural network is a sequence of layers containing the neurons used to learn from data samples. Each layer's neurons receive inputs, process them via an optimizer function, and produce outputs. 
B)  The data is fed into the network via an input layer that specifies the dimensions of the sample data. 
C)  The input layer is followed by hidden layers of neurons that implement the learning and an output layer that produces predictions. The more layers you stack, the deeper the network is (hence the term deep learning). A

Question 2

Which of the following statements a), b) or c) is false?

Accepted Answer

A)  Assuming the IMDb training set samples, training set labels, testing set samples and testing set labels are stored in X_train, y_train, X_test, and y_test, respectively, the following code snippets check their dimensions:
[4]: X_train.shape
[4]: (25000,)
[5]: y_train.shape
[5]: (25000,)
[6]: X_test.shape
[6]: (25000,)
[7]: y_test.shape
[7]: (25000,) 
B)  The arrays y_train and X_test are one-dimensional arrays containing 1s and 0s, indicating whether each review is positive or negative. 
C)  Based on the outputs from the snippets in Part (a), X_train and X_test appear to be one-dimensional. However, their elements actually are lists of integers, each representing one review's contents, as shown in the code below:
[8]: %pprint
[8]: Pretty printing has been turned OFF
[9]: X_train[123]
[9]: [1, 307, 5, 1301, 20, 1026, 2511, 87, 2775, 52, 116, 5, 31, 7, 4, 91, 1220, 102, 13, 28, 110, 11, 6, 137, 13, 115, 219, 141, 35, 221, 956, 54, 13, 16, 11, 2714, 61, 322, 423, 12, 38, 76, 59, 1803, 72, 8, 2, 23, 5, 967, 12, 38, 85, 62, 358, 99] 
D)  All of the above statements are true: 
A)  Assuming the IMDb training set samples, training set labels, testing set samples and testing set labels are stored in X_train, y_train, X_test, and y_test, respectively, the following code snippets check their dimensions:
[4]: X_train.shape
[4]: (25000,)
[5]: y_train.shape
[5]: (25000,)
[6]: X_test.shape
[6]: (25000,)
[7]: y_test.shape
[7]: (25000,) 
B)  The arrays y_train and X_test are one-dimensional arrays containing 1s and 0s, indicating whether each review is positive or negative. 
C)  Based on the outputs from the snippets in Part (a), X_train and X_test appear to be one-dimensional. However, their elements actually are lists of integers, each representing one review's contents, as shown in the code below:
[8]: %pprint
[8]: Pretty printing has been turned OFF
[9]: X_train[123]
[9]: [1, 307, 5, 1301, 20, 1026, 2511, 87, 2775, 52, 116, 5, 31, 7, 4, 91, 1220, 102, 13, 28, 110, 11, 6, 137, 13, 115, 219, 141, 35, 221, 956, 54, 13, 16, 11, 2714, 61, 322, 423, 12, 38, 76, 59, 1803, 72, 8, 2, 23, 5, 967, 12, 38, 85, 62, 358, 99] 
D)  All of the above statements are true: B

Question 3

Which of the following statements a), b) or c) is false?

Accepted Answer

A)  Deep learning can require significant processing power. 
B)  Complex models trained on big-data datasets can take hours, days or even more to train. 
C)  Special high-performance hardware called GPUs (xe "Graphics Processing Unit (GPU)"Graphics Processing Units) and xe "TPU (Tensor Processing Unit)"TPUs (Tensor Processing Units) developed by NVIDIA and Google, respectively, to meet the extraordinary processing demands of edge-of-the-practice deep-learning applications. 
D)  All of the above statements are true. 
A)  Deep learning can require significant processing power. 
B)  Complex models trained on big-data datasets can take hours, days or even more to train. 
C)  Special high-performance hardware called GPUs (xe "Graphics Processing Unit (GPU)"Graphics Processing Units) and xe "TPU (Tensor Processing Unit)"TPUs (Tensor Processing Units) developed by NVIDIA and Google, respectively, to meet the extraordinary processing demands of edge-of-the-practice deep-learning applications. 
D)  All of the above statements are true. D

Question 4

Which of the following statements is false?

Accepted Answer

A)  The following code imports the tensorflow.keras.datasets.mnist module containing the function that loads the MNIST dataset:

from tensorflow.keras.datasets import mnist 
B)  In the version of Keras built into TensorFlow, the Keras module names begin with "tensorflow.". 
C)  TensorFlow uses Keras to execute the deep-learning models. 
D)  The mnist module’s load_data function loads the MNIST training and test-ing sets:

(X_train, y_train), (X_test, y_test) = mnist.load_data()

When you call load_data it will download the MNIST data to your system. The function returns a tuple of two elements containing the training and testing sets. Each element is itself a tuple containing the samples and labels, respectively. 
A)  The following code imports the tensorflow.keras.datasets.mnist module containing the function that loads the MNIST dataset:

from tensorflow.keras.datasets import mnist 
B)  In the version of Keras built into TensorFlow, the Keras module names begin with "tensorflow.". 
C)  TensorFlow uses Keras to execute the deep-learning models. 
D)  The mnist module’s load_data function loads the MNIST training and test-ing sets:

(X_train, y_train), (X_test, y_test) = mnist.load_data()

When you call load_data it will download the MNIST data to your system. The function returns a tuple of two elements containing the training and testing sets. Each element is itself a tuple containing the samples and labels, respectively.

Question 5

Which of the following statements a), b) or c) is false?

Accepted Answer

A)  In the "Machine Learning" chapter, we xe "handwritten digits:classification"xe "classification (machine learning):handwritten digits"classified handwritten digits using the 8-by-8-pixel, low-resolution images from the Digits dataset bundled with Scikit-learn. 
B)  The Digits dataset is based on a subset of the higher-resolution xe "MNIST handwritten digits dataset:Keras"MNIST handwritten digits dataset. 
C)  Recurrent neural networks are common in computer-vision applications, such as recognizing handwritten digits and characters, and recognizing objects in images and video. 
D)  All of the above statements are true. 
A)  In the "Machine Learning" chapter, we xe "handwritten digits:classification"xe "classification (machine learning):handwritten digits"classified handwritten digits using the 8-by-8-pixel, low-resolution images from the Digits dataset bundled with Scikit-learn. 
B)  The Digits dataset is based on a subset of the higher-resolution xe "MNIST handwritten digits dataset:Keras"MNIST handwritten digits dataset. 
C)  Recurrent neural networks are common in computer-vision applications, such as recognizing handwritten digits and characters, and recognizing objects in images and video. 
D)  All of the above statements are true.

Question 6

Which of the following statements is false?

Accepted Answer

A)  The IMDb movie reviews dataset included with Keras contains 25,000 training samples and 25,000 testing samples, each labeled with its positive (1) or negative (0) sentiment. 
B)  The following code imports the xe "modules:tensorflow.keras.datasets"xe "tensorflow.keras.datasets module"tensorflow.keras.datasets.imdb module so we can load the dataset:
From tensorflow.keras.datasets import imdb 
C)  The imdb module's load_data function returns the IMDb training and testing sets. The load_data function enables you to specify the number of unique words to import as part of the training and testing data. The following code loads only the top 10,000 most frequently occurring words:
Number_of_words = 10000
(X_train, y_train), (X_test, y_test) = imdb.load_data(
Num_words=number_of_words) 
D)  The load_data call in Part (c) returns a tuple of two elements containing the samples and labels, respectively. 
A)  The IMDb movie reviews dataset included with Keras contains 25,000 training samples and 25,000 testing samples, each labeled with its positive (1) or negative (0) sentiment. 
B)  The following code imports the xe "modules:tensorflow.keras.datasets"xe "tensorflow.keras.datasets module"tensorflow.keras.datasets.imdb module so we can load the dataset:
From tensorflow.keras.datasets import imdb 
C)  The imdb module's load_data function returns the IMDb training and testing sets. The load_data function enables you to specify the number of unique words to import as part of the training and testing data. The following code loads only the top 10,000 most frequently occurring words:
Number_of_words = 10000
(X_train, y_train), (X_test, y_test) = imdb.load_data(
Num_words=number_of_words) 
D)  The load_data call in Part (c) returns a tuple of two elements containing the samples and labels, respectively.

Question 7

Which of the following statements a), b) or c) is false?

Accepted Answer

A)  TensorBoard is a TensorFlow tool for visualizing data from your deep-learning models as they execute. 
B)  You can view TensorFlow charts showing how the training and validation accuracy and loss values change through the epochs. 
C)  Andrej Karpathy's ConvnetJS tool, trains convnets in your web browser and dynamically visualizes the layers' outputs, including what each convolutional layer "sees" as it learns. 
D)  All of the above statements are true. 
A)  TensorBoard is a TensorFlow tool for visualizing data from your deep-learning models as they execute. 
B)  You can view TensorFlow charts showing how the training and validation accuracy and loss values change through the epochs. 
C)  Andrej Karpathy's ConvnetJS tool, trains convnets in your web browser and dynamically visualizes the layers' outputs, including what each convolutional layer "sees" as it learns. 
D)  All of the above statements are true.

Question 8

Which of the following statements about a max pooling layer a), b) or c) is false?

Accepted Answer

A)  A max pooling layer looks at a pool, then outputs the maximum feature from that pool. 
B)  Unlike convolution, there's no overlap between pools. Once the pool reaches the right edge, the pooling layer moves the pool down by its height-2 rows for a 2-by-2 pool-then continues from left-to-right. Because of the feature reduction in each group, 2-by-2 pooling compresses the number of features by 50%. 
C)  The following code adds a MaxPooling2D layer with a 2-by-2 pool to a model named cnn:
Cnn)add(MaxPooling2D(pool_size=(2, 2))) 
D)  All of the above statements are true. 
A)  A max pooling layer looks at a pool, then outputs the maximum feature from that pool. 
B)  Unlike convolution, there's no overlap between pools. Once the pool reaches the right edge, the pooling layer moves the pool down by its height-2 rows for a 2-by-2 pool-then continues from left-to-right. Because of the feature reduction in each group, 2-by-2 pooling compresses the number of features by 50%. 
C)  The following code adds a MaxPooling2D layer with a 2-by-2 pool to a model named cnn:
Cnn)add(MaxPooling2D(pool_size=(2, 2))) 
D)  All of the above statements are true.

Question 9

Which of the following statements a), b) or c) is false?

Accepted Answer

A)  RNNs for text sequences take into account the relationships among the earlier and later parts of a sequence. 
B)  When determining the meaning of text there can be many words to consider and an arbitrary number of words in between them. 
C)  A Long Short-Term Memory (LSTM) layer makes a neural network convolutional and is optimized to handle learning from sequences. 
D)  All of the above statements are true. 
A)  RNNs for text sequences take into account the relationships among the earlier and later parts of a sequence. 
B)  When determining the meaning of text there can be many words to consider and an arbitrary number of words in between them. 
C)  A Long Short-Term Memory (LSTM) layer makes a neural network convolutional and is optimized to handle learning from sequences. 
D)  All of the above statements are true.

Question 10

The MNIST xe "convnet (convolutional neural network)"convnet's prediction for each MNIST digit will be an array of 10 probabilities, indicating the likelihood that the digit belongs to a particular one of the classes 0 through 9. When we evaluate the model's accuracy, Keras compares the model's predictions to the dataset's labels. To do that, Keras requires both to have the same ________.

Accepted Answer

A)  profile 
B)  aspect 
C)  shape 
D)  frame 
A)  profile 
B)  aspect 
C)  shape 
D)  frame

Question 11

Which of the following statements is false?

Accepted Answer

A)  Keras facilitates experimenting with many deep-learning models and tweaking them in various ways until you find the models that perform best for your applications. 
B)  Deep learning works well only when you have lots of data. 
C)  Transfer learning uses existing knowledge from a previously trained model as the foundation for a new model. 
D)  Data augmentation adds data to a dataset by deriving new data from existing data. For example, in an image dataset, you might rotate the images left and right so the model can learn about objects in different orientations. 
A)  Keras facilitates experimenting with many deep-learning models and tweaking them in various ways until you find the models that perform best for your applications. 
B)  Deep learning works well only when you have lots of data. 
C)  Transfer learning uses existing knowledge from a previously trained model as the foundation for a new model. 
D)  Data augmentation adds data to a dataset by deriving new data from existing data. For example, in an image dataset, you might rotate the images left and right so the model can learn about objects in different orientations.

Question 12

Which of the following statements is false?

Accepted Answer

A)  In a time series, a time step is the next point in time. 
B)  In a text sequence, a "time step" would be the next word in a sequence of words. 
C)  The looping in convolutional neural networks enables them to learn and remember relationships among the data in the sequence. 
D)  The word "good" on its own has positive sentiment. However, when preceded by "not," which appears earlier in the sequence, the sentiment becomes negative. 
A)  In a time series, a time step is the next point in time. 
B)  In a text sequence, a "time step" would be the next word in a sequence of words. 
C)  The looping in convolutional neural networks enables them to learn and remember relationships among the data in the sequence. 
D)  The word "good" on its own has positive sentiment. However, when preceded by "not," which appears earlier in the sequence, the sentiment becomes negative.

Question 13

Which of the following statements a), b) or c) is false?

Accepted Answer

A)  Reproducibility is crucial in scientific studies. 
B)  In deep learning, reproducibility is more difficult because the libraries sequentialize operations that perform floating-point calculations. 
C)  Getting reproducible results in Keras requires a combination of environment settings and code settings that are described in the Keras FAQ. 
D)  All of the above statements are true. 
A)  Reproducibility is crucial in scientific studies. 
B)  In deep learning, reproducibility is more difficult because the libraries sequentialize operations that perform floating-point calculations. 
C)  Getting reproducible results in Keras requires a combination of environment settings and code settings that are described in the Keras FAQ. 
D)  All of the above statements are true.

Question 14

Which of the following are popular predefined word embeddings?

Accepted Answer

A)  GloVe 
B)  Word2Vec 
C)  (a) and (b) 
D)  None of the above. 
A)  GloVe 
B)  Word2Vec 
C)  (a) and (b) 
D)  None of the above.

Question 15

________ neural networks are especially appropriate for computer vision tasks, such as recognizing handwritten digits and characters or recognizing objects (including faces) in images and videos.

Accepted Answer

A)  LSTM 
B)  Recurrent 
C)  Convolutional 
D)  None of the above 
A)  LSTM 
B)  Recurrent 
C)  Convolutional 
D)  None of the above

Question 16

The following code creates a TensorBoard object: 
from tensorflow.keras.callbacks import TensorBoard
import time

tensorboard_callback = TensorBoard(
    log_dir=f'./logs/mnist{time.time()}',   
    histogram_freq=1, write_graph=True)

Which of the following statements a), b) or c) about the above code is false?

Accepted Answer

A)  The log_dir argument is the name of the folder in which this model’s log files will be written. 
B)  The notation './logs/' indicates that we’re creating a new folder within the logs folder you created previously. The preceding code follows that folder with '/mnist' and the current time. Using the time ensures that each new execution of the notebook will have its own log folder. That will enable you to compare multiple executions in TensorBoard. 
C)  The histogram_freq argument is the frequency in epochs that Keras will output to the model’s log files. In this case, we’ll write data to the logs for every epoch. 
D)  When the write_graph argument is True, a graph of the model will be out-put. You can view the graph in the GRAPHS tab in TensorBoard. 
E)  All of the above statements are true. 
A)  The log_dir argument is the name of the folder in which this model’s log files will be written. 
B)  The notation './logs/' indicates that we’re creating a new folder within the logs folder you created previously. The preceding code follows that folder with '/mnist' and the current time. Using the time ensures that each new execution of the notebook will have its own log folder. That will enable you to compare multiple executions in TensorBoard. 
C)  The histogram_freq argument is the frequency in epochs that Keras will output to the model’s log files. In this case, we’ll write data to the logs for every epoch. 
D)  When the write_graph argument is True, a graph of the model will be out-put. You can view the graph in the GRAPHS tab in TensorBoard. 
E)  All of the above statements are true.

Question 17

Which of the following are not automated deep-learning capabilities?

Accepted Answer

A)  Auto-Keras from Texas A&M University's DATA Lab 
B)  Baidu's xe "deep learning EZDL"xe "deep learning:EZDL"xe "EZDL automated deep learning (Baidu)"EZDL 
C)  Google's xe "AutoML"AutoML 
D)  Scikit-learn 
A)  Auto-Keras from Texas A&M University's DATA Lab 
B)  Baidu's xe "deep learning EZDL"xe "deep learning:EZDL"xe "EZDL automated deep learning (Baidu)"EZDL 
C)  Google's xe "AutoML"AutoML 
D)  Scikit-learn

Question 18

Which of the following statements a), b) or c) about neural networks is false?

Accepted Answer

A)  During the training phase, the network calculates values called weights for every connection between the neurons in one layer and those in the next. 
B)  On a neuron-by-neuron basis, each of its inputs is multiplied by that connection's weight, then the maximum of those xe "weighted inputs"weighted inputs is passed to the neuron's activation function. 
C)  The activation function's output determines which neurons to activate based on the inputs-just like the neurons in your brain passing information around in response to inputs coming from your eyes, nose, ears and more. 
D)  All of the above statements are true. 
A)  During the training phase, the network calculates values called weights for every connection between the neurons in one layer and those in the next. 
B)  On a neuron-by-neuron basis, each of its inputs is multiplied by that connection's weight, then the maximum of those xe "weighted inputs"weighted inputs is passed to the neuron's activation function. 
C)  The activation function's output determines which neurons to activate based on the inputs-just like the neurons in your brain passing information around in response to inputs coming from your eyes, nose, ears and more. 
D)  All of the above statements are true.

Question 19

Which of the following statements is false?

Accepted Answer

A)  Deep learning frameworks generally manipulate data in the form of tensors. 
B)  A tensor is basically a one-dimensional array. 
C)  Frameworks like TensorFlow pack all your data into one or more tensors, which they use to perform the mathematical calculations that enable neural networks to learn. 
D)  These tensors can become quite large as the number of dimensions increases and as the richness of the data increases (for example, images, audios and videos are richer than text). 
A)  Deep learning frameworks generally manipulate data in the form of tensors. 
B)  A tensor is basically a one-dimensional array. 
C)  Frameworks like TensorFlow pack all your data into one or more tensors, which they use to perform the mathematical calculations that enable neural networks to learn. 
D)  These tensors can become quite large as the number of dimensions increases and as the richness of the data increases (for example, images, audios and videos are richer than text).

Question 20

Which of the following statements a), b) or c) is false?

Accepted Answer

A)  We've used xe "one-hot encoding[one hot encoding]"one-hot encoding to convert the MNIST dataset's integer labels into xe "categorical data"categorical data. The result for each label was a vector in which all but one element was 0. We could also do that for the index values that represent the words in the IMDb dataset. 
B)  For our IMDb example that processes 10,000 unique words, we'd need a 10,000-by-10,000 array to represent all the words. That's 100,000,000 elements, and almost all the array elements would be 0. This is not an efficient way to encode the data. 
C)  If we were to process all 88,000+ unique words in the IMDb dataset, we'd need an array of nearly eight billion elements. 
D)  All of the above statements are true. 
A)  We've used xe "one-hot encoding[one hot encoding]"one-hot encoding to convert the MNIST dataset's integer labels into xe "categorical data"categorical data. The result for each label was a vector in which all but one element was 0. We could also do that for the index values that represent the words in the IMDb dataset. 
B)  For our IMDb example that processes 10,000 unique words, we'd need a 10,000-by-10,000 array to represent all the words. That's 100,000,000 elements, and almost all the array elements would be 0. This is not an efficient way to encode the data. 
C)  If we were to process all 88,000+ unique words in the IMDb dataset, we'd need an array of nearly eight billion elements. 
D)  All of the above statements are true.

Which of the following statements about Keras neural network components is false?

Which of the following statements a), b) or c) is false?

Which of the following statements a), b) or c) is false?

Which of the following statements is false?

Which of the following statements a), b) or c) is false?

Which of the following statements is false?

Which of the following statements a), b) or c) is false?

Which of the following statements about a max pooling layer a), b) or c) is false?

Which of the following statements a), b) or c) is false?

Which of the following statements is false?

Which of the following statements is false?

Which of the following statements a), b) or c) is false?

Which of the following are popular predefined word embeddings?

________ neural networks are especially appropriate for computer vision tasks, such as recognizing handwritten digits and characters or recognizing objects (including faces) in images and videos.

The following code creates a TensorBoard object: from tensorflow.keras.callbacks import TensorBoard import time tensorboard_callback = TensorBoard( log_dir=f'./logs/mnist{time.time()}', histogram_freq=1, write_graph=True) Which of the following statements a), b) or c) about the above code is false?

Which of the following are not automated deep-learning capabilities?

Which of the following statements a), b) or c) about neural networks is false?

Which of the following statements is false?

Which of the following statements a), b) or c) is false?

Introduction to Computers and Python

Introduction to Python Programming

Control Statements and Program Development

Functions

Sequences: Lists and Tuples

Dictionaries and Sets

Array-Oriented Programming With Num

Strings: a Deeper Look

Files and Exceptions

Object-Oriented Programming

Computer Science Thinking: Recursion, Searching, Sorting and Big O

Natural Language Processing

Data Mining Twitter

Ibm Watson and Cognitive Computing

Machine Learning: Classification, Regression and Clustering

Big Data: Hadoop, Spark, Nosql and Iot

Filters

Exam 16: Deep Learning

Which of the following statements about Keras neural network components is false?

Which of the following statements a), b) or c) is false?

Which of the following statements a), b) or c) is false?

Which of the following statements is false?

Which of the following statements a), b) or c) is false?

Which of the following statements is false?

Which of the following statements a), b) or c) is false?

Which of the following statements about a max pooling layer a), b) or c) is false?

Which of the following statements a), b) or c) is false?

Which of the following statements is false?

Which of the following statements is false?

Which of the following statements a), b) or c) is false?

Which of the following are popular predefined word embeddings?

________ neural networks are especially appropriate for computer vision tasks, such as recognizing handwritten digits and characters or recognizing objects (including faces) in images and videos.

The following code creates a TensorBoard object: from tensorflow.keras.callbacks import TensorBoard import time tensorboard_callback = TensorBoard( log_dir=f'./logs/mnist{time.time()}', histogram_freq=1, write_graph=True) Which of the following statements a), b) or c) about the above code is false?

Which of the following are not automated deep-learning capabilities?

Which of the following statements a), b) or c) about neural networks is false?

Which of the following statements is false?

Which of the following statements a), b) or c) is false?

Introduction to Computers and Python

Introduction to Python Programming

Control Statements and Program Development

Functions

Sequences: Lists and Tuples

Dictionaries and Sets

Array-Oriented Programming With Num

Strings: a Deeper Look

Files and Exceptions

Object-Oriented Programming

Computer Science Thinking: Recursion, Searching, Sorting and Big O

Natural Language Processing

Data Mining Twitter

Ibm Watson and Cognitive Computing

Machine Learning: Classification, Regression and Clustering

Big Data: Hadoop, Spark, Nosql and Iot

Filters