Question 1

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

Accepted Answer

A)  Powerful processors are needed for real-world deep learning because the size of tensors can be enormous and large-tensor operations can place crushing demands on processors. 
B)  NVIDIA GPUs (xe "Graphics Processing Unit (GPU)"Graphics Processing Units)-originally developed for computer gaming-are optimized for the mathematical matrix operations typically performed on tensors, an essential aspect of how deep learning works "under the hood." 
C)  Recognizing that deep learning is crucial to its future, Google developed TPUs (Tensor Processing Units). Google now uses TPUs in its Cloud TPU service, which can perform quadrillions of floating-point operations per second. 
D)  All of the above statements are true. 
A)  Powerful processors are needed for real-world deep learning because the size of tensors can be enormous and large-tensor operations can place crushing demands on processors. 
B)  NVIDIA GPUs (xe "Graphics Processing Unit (GPU)"Graphics Processing Units)-originally developed for computer gaming-are optimized for the mathematical matrix operations typically performed on tensors, an essential aspect of how deep learning works "under the hood." 
C)  Recognizing that deep learning is crucial to its future, Google developed TPUs (Tensor Processing Units). Google now uses TPUs in its Cloud TPU service, which can perform quadrillions of floating-point operations per second. 
D)  All of the above statements are true.

Question 2

People post their research papers at ________ in parallel with going through peer review for formal publication, hoping for fast feedback. So, this site gives you access to extremely current research.

Accepted Answer

A)  https://kerasteam.slack.com. 
B)  https://blog.keras.io. 
C)  http://keras.io. 
D)  https://arXiv.org 
A)  https://kerasteam.slack.com. 
B)  https://blog.keras.io. 
C)  http://keras.io. 
D)  https://arXiv.org

Question 3

With only two possible outputs, we use the ________ loss function.

Accepted Answer

A)  mean_squared_error 
B)  binary_compression 
C)  categorical_crossentropy 
D)  binary_crossentropy 
A)  mean_squared_error 
B)  binary_compression 
C)  categorical_crossentropy 
D)  binary_crossentropy

Question 4

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

Accepted Answer

A)  With deep learning networks, there's so much complexity and so much going on internally that's hidden from you that it's difficult to know and fully understand all the details. This creates challenges in testing, debugging and updating models and algorithms. 
B)  Deep learning learns the features but there may be enormous numbers of them, and they may not be apparent to you. 
C)  Google provides the TensorBoard tool for visualizing neural networks implemented in TensorFlow and Keras. A TensorBoard dashboard visualizes data from a deep learning model that can give you insights into how well your model is learning and potentially help you tune its hyperparameters. 
D)  All of the above statements are true. 
A)  With deep learning networks, there's so much complexity and so much going on internally that's hidden from you that it's difficult to know and fully understand all the details. This creates challenges in testing, debugging and updating models and algorithms. 
B)  Deep learning learns the features but there may be enormous numbers of them, and they may not be apparent to you. 
C)  Google provides the TensorBoard tool for visualizing neural networks implemented in TensorFlow and Keras. A TensorBoard dashboard visualizes data from a deep learning model that can give you insights into how well your model is learning and potentially help you tune its hyperparameters. 
D)  All of the above statements are true.

Question 5

Which of the following statements about Anaconda environments is false?

Accepted Answer

A)  The Anaconda Python distribution makes it easy to create custom environments. 
B)  Custom environments are separate configurations in which you can install specific python and library version. These can help with xe "reproducibility"reproducibility if your code is specific to particular software and library versions and combinations. 
C)  Anaconda's default environment is called the root environment and is created when you install Anaconda and contains all the Python libraries that come with Anaconda. Unless you specify otherwise, additional libraries you install also are placed there. 
D)  Custom environments give you control over the specific libraries you wish to install for your specific tasks. 
A)  The Anaconda Python distribution makes it easy to create custom environments. 
B)  Custom environments are separate configurations in which you can install specific python and library version. These can help with xe "reproducibility"reproducibility if your code is specific to particular software and library versions and combinations. 
C)  Anaconda's default environment is called the root environment and is created when you install Anaconda and contains all the Python libraries that come with Anaconda. Unless you specify otherwise, additional libraries you install also are placed there. 
D)  Custom environments give you control over the specific libraries you wish to install for your specific tasks.

Question 6

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

Accepted Answer

A)  The following code imports several commonly used convnet layer classes from the xe "modules:tensorflow.keras.layers"xe "tensorflow.keras.layers module"tensorflow.keras.layers module:
From tensorflow.keras.layers import Conv2D, Dense, Flatten, MaxPooling2D 
B)  A xe "convolution layer"convolution layer uses the relationships between pixels that are close to one another to learn useful features (or patterns) in large areas of each sample. 
C)  The areas that convolution learns from are called kernels or patches. 
D)  All of the above statements are true. 
A)  The following code imports several commonly used convnet layer classes from the xe "modules:tensorflow.keras.layers"xe "tensorflow.keras.layers module"tensorflow.keras.layers module:
From tensorflow.keras.layers import Conv2D, Dense, Flatten, MaxPooling2D 
B)  A xe "convolution layer"convolution layer uses the relationships between pixels that are close to one another to learn useful features (or patterns) in large areas of each sample. 
C)  The areas that convolution learns from are called kernels or patches. 
D)  All of the above statements are true.

Question 7

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

Accepted Answer

A)  Numeric features in data samples may have value ranges that vary widely. Deep learning networks perform better on data that is scaled either into the range 0.0 to 1.0, or to a range for which the data's mean is 1.0 and its standard deviation is 0.0. Getting your data into one of these forms is known as xe "normalized data"normalization. 
B)  In MNIST, each pixel is an integer in the range 0-255. 
C)  Assuming X_train and X_test represent the MNIST samples, the following code converts the MNIST pixel values to 32-bit (4-byte) floating-point numbers using the xe "NumPy:convert array to floating-point values"NumPy array method astype, then divides every element in the resulting array by 255, producing normalized values in the range 0.0-1.0:
X_train = X_train.astype('float32') / 255
X_test = X_test.astype('float32') / 255 
D)  All of the above statements are true. 
A)  Numeric features in data samples may have value ranges that vary widely. Deep learning networks perform better on data that is scaled either into the range 0.0 to 1.0, or to a range for which the data's mean is 1.0 and its standard deviation is 0.0. Getting your data into one of these forms is known as xe "normalized data"normalization. 
B)  In MNIST, each pixel is an integer in the range 0-255. 
C)  Assuming X_train and X_test represent the MNIST samples, the following code converts the MNIST pixel values to 32-bit (4-byte) floating-point numbers using the xe "NumPy:convert array to floating-point values"NumPy array method astype, then divides every element in the resulting array by 255, producing normalized values in the range 0.0-1.0:
X_train = X_train.astype('float32') / 255
X_test = X_test.astype('float32') / 255 
D)  All of the above statements are true.

Question 8

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

Accepted Answer

A)  To xe "reduce dimensionality"reduce ambiguity, RNNs that process text sequences typically begin with an embedding layer that encodes each word in a compact xe "dense-vector representation"dense-vector representation. 
B)  The vectors produced by the embedding layer also capture the word's context-that is, how a given word relates to the words around it. 
C)  An embedding layer enables the RNN to learn word relationships among the training data. 
D)  All of the above statements are true. 
A)  To xe "reduce dimensionality"reduce ambiguity, RNNs that process text sequences typically begin with an embedding layer that encodes each word in a compact xe "dense-vector representation"dense-vector representation. 
B)  The vectors produced by the embedding layer also capture the word's context-that is, how a given word relates to the words around it. 
C)  An embedding layer enables the RNN to learn word relationships among the training data. 
D)  All of the above statements are true.

Question 9

The ________ activation function, which is preferred for xe "binary classification"binary classification, reduces arbitrary values into the range 0.0-1.0, producing a probability.

Accepted Answer

A)  softmax 
B)  relu 
C)  sigmoid 
D)  softplus 
A)  softmax 
B)  relu 
C)  sigmoid 
D)  softplus

Question 10

A Keras ________ layer reshapes its input to one dimension.

Accepted Answer

A)  Dropout 
B)  Masking 
C)  Dense 
D)  Flatten 
A)  Dropout 
B)  Masking 
C)  Dense 
D)  Flatten

Question 11

Which of the following statements is false?

Accepted Answer

A)  The pad_sequences utility function (module tensorflow.keras.preprocessing.sequence) reshapes the rows in an array of to the number of features specified by the maxlen argument (200) and returns a two-dimensional array:
[16]: words_per_review = 200
[17]: from tensorflow.keras.preprocessing.sequence import pad_sequences
[18]: X_train = pad_sequences(X_train,
Maxlen=words_per_review) 
B)  If a sample has more features, pad_sequences truncates it to the specified length. 
C)  If a sample has fewer features, pad_sequences adds space characters to the beginning of the sequence to pad it to the specified length. 
D)  You can confirm X_train's new shape with the array's shape attribute:
[19]: X_train.shape
[19]: (25000, 200) 
A)  The pad_sequences utility function (module tensorflow.keras.preprocessing.sequence) reshapes the rows in an array of to the number of features specified by the maxlen argument (200) and returns a two-dimensional array:
[16]: words_per_review = 200
[17]: from tensorflow.keras.preprocessing.sequence import pad_sequences
[18]: X_train = pad_sequences(X_train,
Maxlen=words_per_review) 
B)  If a sample has more features, pad_sequences truncates it to the specified length. 
C)  If a sample has fewer features, pad_sequences adds space characters to the beginning of the sequence to pad it to the specified length. 
D)  You can confirm X_train's new shape with the array's shape attribute:
[19]: X_train.shape
[19]: (25000, 200)

Question 12

Which of the following statements is false?

Accepted Answer

A)  Keras is to xe "deep learning"deep learning as xe "scikit-learn (sklearn) machine-learning library"Scikit-learn is to xe "machine learning"machine learning. 
B)  Deep learning models are complex and require an extensive mathematical background to understand their inner workings. 
C)  Both Keras and Scikit-learn encapsulate the sophisticated mathematics of their models-developers need only define, parameterize and manipulate objects. 
D)  With Keras, you build your models primarily from custom components you develop to meet your unique requirements. 
A)  Keras is to xe "deep learning"deep learning as xe "scikit-learn (sklearn) machine-learning library"Scikit-learn is to xe "machine learning"machine learning. 
B)  Deep learning models are complex and require an extensive mathematical background to understand their inner workings. 
C)  Both Keras and Scikit-learn encapsulate the sophisticated mathematics of their models-developers need only define, parameterize and manipulate objects. 
D)  With Keras, you build your models primarily from custom components you develop to meet your unique requirements.

Question 13

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

Accepted Answer

A)  One-hot encoding converts data into arrays of 1.0s and 0.0s in which only one element is 1.0 and the rest are 0.0s. 
B)  For MNIST targets, the one-hot-encoded values will be 10-by-10 arrays representing the categories 0 through 9. 
C)  We know precisely which category each digit belongs to, so the categorical representation of a digit label will consist of a 1.0 at that digit's index and 0.0s for all the other elements. 
D)  All of the above statements are true. 
A)  One-hot encoding converts data into arrays of 1.0s and 0.0s in which only one element is 1.0 and the rest are 0.0s. 
B)  For MNIST targets, the one-hot-encoded values will be 10-by-10 arrays representing the categories 0 through 9. 
C)  We know precisely which category each digit belongs to, so the categorical representation of a digit label will consist of a 1.0 at that digit's index and 0.0s for all the other elements. 
D)  All of the above statements are true.

Question 14

To use TensorBoard, before you fit your model, you need to configure a TensorBoard object, which the model will use to write data into a specified folder that TensorBoard monitors. This TensorBoard object is known as a ________ in Keras.

Accepted Answer

A)  callforward 
B)  entry point 
C)  callback 
D)  None of the above. 
A)  callforward 
B)  entry point 
C)  callback 
D)  None of the above.

Question 15

Once you've added all the layers to a Keras neural network, you complete the Keras model by calling its compile method, as in: cnn.compile(optimizer='adam',
Loss='categorical_crossentropy',
Metrics=['accuracy'])
Which of the following statements about the arguments is false?

Accepted Answer

A)  optimizer='adam' specifies the optimizer this model will use to adjust the weights throughout the neural network as it learns. 
B)  There are many optimizers -xe "optimizer:'adam'"xe "adam optimizer[adam optimizer]"'adam' performs well across a wide variety of models. 
C)  loss='xe "categorical_crossentropy loss function"xe "loss function:categorical_crossentropy"categorical_crossentropy' specifies the xe "loss function"loss function used by the optimizer in multi-classification networks like our convnet, which predicts 10 classes. As the neural network learns, the optimizer attempts to maximize the values returned by the loss function. The greater the loss, the better the neural network is at predicting what each image is. 
D)  metrics=['accuracy']-This is a list of the metrics that the network will produce to help you evaluate the model. We use the xe "accuracy of a model"accuracy metric to check the percentage of correct predictions. 
A)  optimizer='adam' specifies the optimizer this model will use to adjust the weights throughout the neural network as it learns. 
B)  There are many optimizers -xe "optimizer:'adam'"xe "adam optimizer[adam optimizer]"'adam' performs well across a wide variety of models. 
C)  loss='xe "categorical_crossentropy loss function"xe "loss function:categorical_crossentropy"categorical_crossentropy' specifies the xe "loss function"loss function used by the optimizer in multi-classification networks like our convnet, which predicts 10 classes. As the neural network learns, the optimizer attempts to maximize the values returned by the loss function. The greater the loss, the better the neural network is at predicting what each image is. 
D)  metrics=['accuracy']-This is a list of the metrics that the network will produce to help you evaluate the model. We use the xe "accuracy of a model"accuracy metric to check the percentage of correct predictions.

Question 16

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

Accepted Answer

A)  You should always get to know the data before working with it. 
B)  The following snippets check the dimensions of the MNIST training set images (X_train), training set labels (y_train), testing set images (X_test) and testing set labels (y_test):
[3]: X_train.shape
[3]: (60000, 28, 28)
[4]: y_train.shape
[4]: (60000,)
[5]: X_test.shape
[5]: (10000, 28, 28)
[6]: y_test.shape
[6]: (10000,) 
C)  You can see from X_train's and X_test's shapes that the MNIST images are the same resolution as those in Scikit-learn's Digits dataset. 
D)  All of the above statements are true. 
A)  You should always get to know the data before working with it. 
B)  The following snippets check the dimensions of the MNIST training set images (X_train), training set labels (y_train), testing set images (X_test) and testing set labels (y_test):
[3]: X_train.shape
[3]: (60000, 28, 28)
[4]: y_train.shape
[4]: (60000,)
[5]: X_test.shape
[5]: (10000, 28, 28)
[6]: y_test.shape
[6]: (10000,) 
C)  You can see from X_train's and X_test's shapes that the MNIST images are the same resolution as those in Scikit-learn's Digits dataset. 
D)  All of the above statements are true.

Question 17

Consider the following code: cnn.add(Dense(units=10, activation='softmax'))
Which of the following statements a), b) or c) about our convolutional neural net that recognizes MNIST digits is false?

Accepted Answer

A)  Our convnet's final layer in the preceding snippet is a Dense layer that classifies the inputs into neurons representing the classes 0 through 9. 
B)  The softmax activation function converts the values of these remaining 10 neurons into categorical string labels '0' through '9'. 
C)  The neuron that produces the highest probability represents the prediction for a given digit image. 
D)  All of the above statements are true. 
A)  Our convnet's final layer in the preceding snippet is a Dense layer that classifies the inputs into neurons representing the classes 0 through 9. 
B)  The softmax activation function converts the values of these remaining 10 neurons into categorical string labels '0' through '9'. 
C)  The neuron that produces the highest probability represents the prediction for a given digit image. 
D)  All of the above statements are true.

Question 18

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

Accepted Answer

A)  TensorBoard monitors a folder you specify looking for files output by models during training. 
B)  TensorBoard loads the data from that folder into a browser-based dashboard. 
C)  TensorBoard can load data from multiple models at once and you can choose which to visualize. This makes it easy to compare several different models or multiple runs of the same model. 
D)  All of the above statements are true. 
A)  TensorBoard monitors a folder you specify looking for files output by models during training. 
B)  TensorBoard loads the data from that folder into a browser-based dashboard. 
C)  TensorBoard can load data from multiple models at once and you can choose which to visualize. This makes it easy to compare several different models or multiple runs of the same model. 
D)  All of the above statements are true.

Question 19

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

Accepted Answer

A)  Deep learning is a form of machine learning that uses artificial neural networks to learn. 
B)  An artificial neural network is a software construct that operates similarly to how scientists believe our brains work. 
C)  Our biological xe "central nervous system"nervous systems are controlled via xe "neuron:in biology"neurons that communicate with one another along pathways called xe "synapse in biology"synapses. As we learn, the specific neurons that enable us to perform a given task, like walking, communicate with one another more efficiently. 
D)  All of the above statements are true. 
A)  Deep learning is a form of machine learning that uses artificial neural networks to learn. 
B)  An artificial neural network is a software construct that operates similarly to how scientists believe our brains work. 
C)  Our biological xe "central nervous system"nervous systems are controlled via xe "neuron:in biology"neurons that communicate with one another along pathways called xe "synapse in biology"synapses. As we learn, the specific neurons that enable us to perform a given task, like walking, communicate with one another more efficiently. 
D)  All of the above statements are true.

Question 20

Which of the following statements a), b) or c) is false regarding decoding IMDb movie reviews?

Accepted Answer

A)  The following snippet gets the word-to-index dictionary by calling the function get_word_index from the tensorflow.keras.datasets.imdb module:
[10]: word_to_index = imdb.get_word_index() 
B)  The word 'great' might appear in a positive movie review, so the following code checks whether it's in the dictionary:
[11]: word_to_index['great']
[11]: 84 
C)  According to the Part (b) output, 'great' is the dataset's 84th most frequent word. If you use an expression like the one in Part (b) to look up a word that's not in the dictionary, you'll get an exception. 
D)  All of the above statements are true. 
A)  The following snippet gets the word-to-index dictionary by calling the function get_word_index from the tensorflow.keras.datasets.imdb module:
[10]: word_to_index = imdb.get_word_index() 
B)  The word 'great' might appear in a positive movie review, so the following code checks whether it's in the dictionary:
[11]: word_to_index['great']
[11]: 84 
C)  According to the Part (b) output, 'great' is the dataset's 84th most frequent word. If you use an expression like the one in Part (b) to look up a word that's not in the dictionary, you'll get an exception. 
D)  All of the above statements are true.

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

People post their research papers at ________ in parallel with going through peer review for formal publication, hoping for fast feedback. So, this site gives you access to extremely current research.

With only two possible outputs, we use the ________ loss function.

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

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

The ________ activation function, which is preferred for xe "binary classification"binary classification, reduces arbitrary values into the range 0.0-1.0, producing a probability.

A Keras ________ layer reshapes its input to one dimension.

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?

To use TensorBoard, before you fit your model, you need to configure a TensorBoard object, which the model will use to write data into a specified folder that TensorBoard monitors. This TensorBoard object is known as a ________ in Keras.

Once you've added all the layers to a Keras neural network, you complete the Keras model by calling its compile method, as in: cnn.compile(optimizer='adam', Loss='categorical_crossentropy', Metrics=['accuracy']) Which of the following statements about the arguments is false?

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

Consider the following code: cnn.add(Dense(units=10, activation='softmax')) Which of the following statements a), b) or c) about our convolutional neural net that recognizes MNIST digits 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 a), b) or c) is false regarding decoding IMDb movie reviews?

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 a), b) or c) is false?

People post their research papers at ________ in parallel with going through peer review for formal publication, hoping for fast feedback. So, this site gives you access to extremely current research.

With only two possible outputs, we use the ________ loss function.

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

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

The ________ activation function, which is preferred for xe "binary classification"binary classification, reduces arbitrary values into the range 0.0-1.0, producing a probability.

A Keras ________ layer reshapes its input to one dimension.

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?

To use TensorBoard, before you fit your model, you need to configure a TensorBoard object, which the model will use to write data into a specified folder that TensorBoard monitors. This TensorBoard object is known as a ________ in Keras.

Once you've added all the layers to a Keras neural network, you complete the Keras model by calling its compile method, as in: cnn.compile(optimizer='adam', Loss='categorical_crossentropy', Metrics=['accuracy']) Which of the following statements about the arguments is false?

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

Consider the following code: cnn.add(Dense(units=10, activation='softmax')) Which of the following statements a), b) or c) about our convolutional neural net that recognizes MNIST digits 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 a), b) or c) is false regarding decoding IMDb movie reviews?

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