Scribd Logo
Upload

Welcome to Scribd!

  • 4K views

    CASE STUDY - GANS - CIFAR - Quiz - Attempt Review

    Uploaded by

    vinay Murakambattu
    1. The quiz reviewed a student's attempt on a quiz about generative adversarial networks (GANs) and the CIFAR-10 dataset. 2. The student answered 12 out of 15 questions correctly and received a score of 12/15 or 80%. 3. The questions covered topics like the components of GANs, challenges in training GANs, the purpose of different layers, and characteristics of the CIFAR-10 dataset.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    CASE STUDY - GANS - CIFAR - Quiz - Attempt Review

    Uploaded by

    vinay Murakambattu
    4K views6 pages
    1. The quiz reviewed a student's attempt on a quiz about generative adversarial networks (GANs) and the CIFAR-10 dataset. 2. The student answered 12 out of 15 questions correctly and received a score of 12/15 or 80%. 3. The questions covered topics like the components of GANs, challenges in training GANs, the purpose of different layers, and characteristics of the CIFAR-10 dataset.

    Original Title

    CASE STUDY - GANS - CIFAR - Quiz_ Attempt review

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    1. The quiz reviewed a student's attempt on a quiz about generative adversarial networks (GANs) and the CIFAR-10 dataset. 2. The student answered 12 out of 15 questions correctly and received a score of 12/15 or 80%. 3. The questions covered topics like the components of GANs, challenges in training GANs, the purpose of different layers, and characteristics of the CIFAR-10 dataset.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    4K views6 pages

    CASE STUDY - GANS - CIFAR - Quiz - Attempt Review

    Uploaded by

    vinay Murakambattu
    1. The quiz reviewed a student's attempt on a quiz about generative adversarial networks (GANs) and the CIFAR-10 dataset. 2. The student answered 12 out of 15 questions correctly and received a score of 12/15 or 80%. 3. The questions covered topics like the components of GANs, challenges in training GANs, the purpose of different layers, and characteristics of the CIFAR-10 dataset.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 6

    1/27/24, 7:41 AM CASE STUDY - GANS - CIFAR - Quiz: Attempt review


     Dashboard / Primer 2.0 - Infrastructure Security / Stage 1 / Gen AI / Generative Adversarial Networks

    Quiz review
    Started on Saturday, 27 January 2024, 7:37 AM
    State Finished
    Completed on Saturday, 27 January 2024, 7:41 AM
    Time taken 4 mins 16 secs
    Marks 12.00/15.00
    Grade 80.00 out of 100.00

    Question 1
    Correct

    Mark 1.00 out of 1.00

    Which architecture can help address convergence issues in traditional GANs?

    LSTM
    RNN
    46684
    CNN
    DBN
    WGAN

    The correct answer is: WGAN

    Question 2
    Correct

    Mark 1.00 out of 1.00 46684


    In the generator code, what is the purpose of the Reshape layer?

    To critique the images


    To normalize the image values
    To reshape the dense layer into a 3D tensor for images
    To upsample the images
    To flatten the images

    46684
    The correct answer is: To reshape the dense layer into a 3D tensor for images

    https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=1094059&cmid=7551 1/6
    1/27/24, 7:41 AM CASE STUDY - GANS - CIFAR - Quiz: Attempt review

    Question 3
    Correct

    Mark 1.00 out of 1.00

    What does the discriminator do in a GAN?

    Both create and evaluate images


    Enhances image resolution
    Creates images
    Combines images
    Evaluates if an image is real or fake

    The correct answer is: Evaluates if an image is real or fake

    Question 4
    Correct

    Mark 1.00 out of 1.00


    46684
    Which challenge refers to the generator producing limited varieties or even the same sample every time?

    Training Instability
    Data Augmentation
    All of the given options
    Convergence Issues
    Mode Collapse

    The correct answer is: Mode Collapse


    46684
    Question 5
    Incorrect

    Mark 0.00 out of 1.00

    Which technique can help in dealing with training instability in GANs?

    Dropout
    Noise addition

    46684
    Gradient clipping
    Data augmentation
    All of the given options 

    The correct answer is: Gradient clipping

    https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=1094059&cmid=7551 2/6
    1/27/24, 7:41 AM CASE STUDY - GANS - CIFAR - Quiz: Attempt review

    Question 6
    Incorrect

    Mark 0.00 out of 1.00

    Which of the following is NOT a feedback given to the generator during training?

    This image looks like a car 


    This image is pixelated
    This is a fake image
    This is a genuine image
    This image looks blurry

    The correct answer is: This image is pixelated

    Question 7
    Correct

    Mark 1.00 out of 1.00


    46684
    Which activation function is used in the final layer of the generator model?

    sigmoid
    relu
    leakyrelu
    softmax
    tanh

    The correct answer is: tanh


    46684
    Question 8
    Correct

    Mark 1.00 out of 1.00

    How many images are there in each class of the CIFAR-10 dataset?

    12000
    15000

    46684
    5000
    10000
    6000

    The correct answer is: 6000

    https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=1094059&cmid=7551 3/6
    1/27/24, 7:41 AM CASE STUDY - GANS - CIFAR - Quiz: Attempt review

    Question 9
    Correct

    Mark 1.00 out of 1.00

    Which of the following best describes the role of the generator in a GAN?

    None of the given options


    To critique images
    To combine images
    To evaluate the loss
    To produce images

    The correct answer is: To produce images

    Question 10
    Correct

    Mark 1.00 out of 1.00


    46684
    During training, what does the generator use to improve itself?

    Feedback from the user


    Feedback from the discriminator
    CIFAR-10 dataset
    Real images
    Feedback from both the user and the discriminator

    46684
    The correct answer is: Feedback from the discriminator

    Question 11
    Correct

    Mark 1.00 out of 1.00

    In the discriminator's code, which layer helps in reducing the dimensions of the input image?

    UpSampling2D
    BatchNormalization

    46684
    Reshape
    Dense
    Conv2D with strides

    The correct answer is: Conv2D with strides

    https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=1094059&cmid=7551 4/6
    1/27/24, 7:41 AM CASE STUDY - GANS - CIFAR - Quiz: Attempt review

    Question 12
    Incorrect

    Mark 0.00 out of 1.00

    What is used to refine the models during training?

    Batch Normalization
    LeakyReLU
    Adam Optimizer
    Conv2D
    All of the given options 

    The correct answer is: Adam Optimizer

    Question 13
    Correct

    Mark 1.00 out of 1.00


    46684
    What are the two main components of a GAN?

    Discriminator & Evaluator


    Generator & Evaluator
    Generator & UpSampler
    Discriminator & Sampler
    Generator & Discriminator

    The correct answer is: Generator & Discriminator


    46684
    Question 14
    Correct

    Mark 1.00 out of 1.00

    Why might someone want to use GANs on the CIFAR-10 dataset?

    To generate novel and relevant images to augment dataset


    To delete images from the dataset

    46684
    To reduce the size of the dataset
    To critique the images in the dataset
    To classify the images in the dataset

    The correct answer is: To generate novel and relevant images to augment dataset

    https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=1094059&cmid=7551 5/6
    1/27/24, 7:41 AM CASE STUDY - GANS - CIFAR - Quiz: Attempt review

    Question 15
    Correct

    Mark 1.00 out of 1.00

    In the provided code, why is discriminator.trainable set to False when setting up the combined system?

    To prevent overfitting
    None of the given options
    To increase discriminator's accuracy
    To make sure only the generator is trained in this step
    To speed up training

    The correct answer is: To make sure only the generator is trained in this step

    ◄ Case Study - GAN - CIFAR

    Jump to... 46684


    Sequence Generation with RNNs - Pre Quiz ►

    46684

    46684

    https://accenturelearning.tekstac.com/mod/quiz/review.php?attempt=1094059&cmid=7551 6/6

    You might also like