Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 354 views

    Deep Learning KCS078

    Uploaded by

    xefedoy533
    This document contains the questions for a B.Tech deep learning theory examination. It has 7 sections with multiple choice and long answer questions. Section A contains 10 short answer questions about machine learning applications, Boltzmann machines, convolutional neural network layers, linear models, non-linearities in neural networks, perceptron limitations, convolutions for images, GPUs for deep learning, and face detection algorithms. Section B has 3 long answer questions about deep vs shallow networks, convolutional network architecture, and LSTMs. Section C contains long answer explanations of gradient descent vs stochastic gradient descent or GANs. The remaining sections ask students to explain semi-supervised learning, backpropagation, PCA vs RNNs, privacy implications of facial recognition, and

    Copyright:

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

    Deep Learning KCS078

    Uploaded by

    xefedoy533
    354 views2 pages
    This document contains the questions for a B.Tech deep learning theory examination. It has 7 sections with multiple choice and long answer questions. Section A contains 10 short answer questions about machine learning applications, Boltzmann machines, convolutional neural network layers, linear models, non-linearities in neural networks, perceptron limitations, convolutions for images, GPUs for deep learning, and face detection algorithms. Section B has 3 long answer questions about deep vs shallow networks, convolutional network architecture, and LSTMs. Section C contains long answer explanations of gradient descent vs stochastic gradient descent or GANs. The remaining sections ask students to explain semi-supervised learning, backpropagation, PCA vs RNNs, privacy implications of facial recognition, and

    Original Title

    DEEP-LEARNING-KCS078

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document contains the questions for a B.Tech deep learning theory examination. It has 7 sections with multiple choice and long answer questions. Section A contains 10 short answer questions about machine learning applications, Boltzmann machines, convolutional neural network layers, linear models, non-linearities in neural networks, perceptron limitations, convolutions for images, GPUs for deep learning, and face detection algorithms. Section B has 3 long answer questions about deep vs shallow networks, convolutional network architecture, and LSTMs. Section C contains long answer explanations of gradient descent vs stochastic gradient descent or GANs. The remaining sections ask students to explain semi-supervised learning, backpropagation, PCA vs RNNs, privacy implications of facial recognition, and

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    354 views2 pages

    Deep Learning KCS078

    Uploaded by

    xefedoy533
    This document contains the questions for a B.Tech deep learning theory examination. It has 7 sections with multiple choice and long answer questions. Section A contains 10 short answer questions about machine learning applications, Boltzmann machines, convolutional neural network layers, linear models, non-linearities in neural networks, perceptron limitations, convolutions for images, GPUs for deep learning, and face detection algorithms. Section B has 3 long answer questions about deep vs shallow networks, convolutional network architecture, and LSTMs. Section C contains long answer explanations of gradient descent vs stochastic gradient descent or GANs. The remaining sections ask students to explain semi-supervised learning, backpropagation, PCA vs RNNs, privacy implications of facial recognition, and

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 2

    Printed Pages: 02 Sub Code: KCS - 078

    Paper Id: 2 3 1 5 4 7 Roll No.

    B.TECH
    (SEM VII) THEORY EXAMINATION 2022-23
    DEEP LEARNING
    Time: 3 Hours Total Marks: 100
    Note: Attempt all Sections. If you require any missing data, then choose suitably.

    SECTION A

    1. Attempt all questions in brief. 2 x 10 = 20


    (a) What are the applications of Machine Learning?
    (b) Describe the Boltzmann Machine.
    (c) Is it possible to build deep learning models based solely on linear regression?
    Explain.
    (d) Define the different layers of a convolutional neural network.
    (e) Explain the linear models
    (f) Why is it important to introduce non-linearities in a neural network?
    (g) What are the limitations of using a perceptron?
    (h) Why do we use convolutions for images instead of using fully connected
    layers?`

    2
    90
    (i) Why are GPUs important for implementing deep learning models?

    13
    _2

    (j) Which is the best algorithm for face detection ?

    2.
    P1

    24
    SECTION B

    5.
    3D

    .5
    P2

    2. Attempt any three of the following: 17 10 x 3 = 30


    Q

    |1
    (a) Difference between Deep and Shallow Network.
    (b) Draw and explain the architecture of Convolutional Networks.
    4

    (c) Why CNN is preferred over ANN for Image Classification tasks even though it
    :0

    is possible to solve image classification using ANN?


    23

    (d) Explain LSTM (Long Short Term Memory ). Give some famous applications
    :

    of LSTM.
    13

    (e) Explain Image Captioning in Deep Learning.


    3
    02

    SECTION C
    -2
    01

    3. Attempt any one part of the following: 10 x 1 = 10


    3-

    (a) Explain the difference between Gradient Descent and Stochastic Gradient
    |1

    Descent.
    (b) ExplainGAN and its models. Name and describe different types of GANs.

    4. Attempt any one part of the following: 10 x 1 = 10


    (a) Examine the Semi –Supervised learning.
    (b) Demonstrate deep learning. Explain its uses, application and history.

    QP23DP1_290 | 13-01-2023 13:23:04 | 117.55.242.132


    5. Attempt any one part of the following: 10 x 1 = 10
    (a) Explain Back propagation with its algorithm.
    (b) Write short notes :-
    i) Deep Reinforcement
    ii) Autoencoder Architecture
    iii) VGG
    iv) SOA

    6. Attempt any one part of the following: 10 x 1 = 10


    (a) Compare PCA (Principle Component Analysis ) and RNN.
    (b) Discuss how batch gradient descent and stochastic gradient descent are
    different.

    7. Attempt any one part of the following: 10 x 1 = 10


    (a) Demonstrate how the privacy will be affected when facial recognition gets
    used by private companies?
    (b) How AI and Neuroscience drive each other forwards? Explain.

    2
    90

    13
    _2

    2.
    P1

    24
    5.
    3D

    .5
    P2

    17
    Q

    |1
    4
    :0
    : 23
    13
    3
    02
    -2
    01
    3-
    |1

    QP23DP1_290 | 13-01-2023 13:23:04 | 117.55.242.132

    You might also like