Scribd Logo
Upload

Welcome to Scribd!

  • 39 views

    DL Unit Wise Important Questions

    Uploaded by

    Seetha Laxmi
    DEEP LEARNING

    Copyright:

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

    DL Unit Wise Important Questions

    Uploaded by

    Seetha Laxmi
    39 views2 pages
    DEEP LEARNING

    Original Title

    DL UNIT WISE IMPORTANT QUESTIONS

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    DEEP LEARNING

    Copyright:

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

    DL Unit Wise Important Questions

    Uploaded by

    Seetha Laxmi
    DEEP LEARNING

    Copyright:

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

    DEEP LEARNING UNIT WISE IMPORTANT QUESTIONS

    UNIT 1
    1)Explain the concepts of Scalar, Vectors and Matrices and tensor in deep learning.
    2)Describe the concept of probability Distributions.
    3)What is Gradient based optimisation in learning.
    4)Explain the below terms:
    o Capacity
    o Overfitting and Underfitting.
    5)Discuss about hyperparameters and validation sets.
    6)Describe the concept of bias and variance .How to overcome the bias and variance.
    7)Discuss in detail about Stochastic gradient descent.
    8)What are the challenges motivating in Deep learning.
    9)What do you mean by deep networks.Explain the Deep feed forward networks.

    UNIT 2:

    1)What is Convolutional Neural networks.Explain the operation involved in it.


    2)Explain the sparse interactions ,parameter sharing and equivariance in CNN.
    3)Explain the concept and types of pooling.
    4)Discuss three types of Convolution variant(Strided,Tiled and Transposed and Dilated )
    5)What is CNN learning and explain about the Nonlinearity Functions -- Loss Functions.
    6)Explain the concept of regularisation in CNN.

    UNIT 3
    1)Explain the architecture of RNN.
    2)Discuss about the unfold graph in CNN.
    3)Explain the concept of acceptor, Encoder and transducer in RNN design patterns.
    4)Explain the gradient Computation and sequence modeling conditioned on contexts.
    5)Discuss the architecture of bidirectional RNN.
    6)Discuss the architecture of Sequence to sequence RNN.
    7)Explain the Concept and architecture of Deep recurrent networks.
    8)Explain Recursive RNN with neat diagram
    9)Explain the concept of Long term dependencies.

    UNIT 4

    1.Explain all the performance metrics used in model evaluation.


    2.Describe the baseline models.
    3.What is hyperparameter?Explain the two types of hyperparameter.
    4.Explain in detail about Grid and random search.

    UNIT 5

    1.Explain the architecture of autoencoders with near Diagram.Write down their uses and
    applications.
    2.Describe about the Undercomplete and Regularised autoencoders
    3.Explain about the sparse and Denoising Autoencoders in detail.
    4.Explain the Stochastic Encoder decoder and Variational autoencoders.
    5.Explain the Deep generative model with Boltzmann machine.
    6.Explain the concept and working of deep belief network.
    7.Describe GAN in detail.

    You might also like