Scribd Logo
Upload

Welcome to Scribd!

  • 5 views

    ASP UNIT-2 Question Bank

    Uploaded by

    saipavankumar.vemuri69

    Copyright:

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

    ASP UNIT-2 Question Bank

    Uploaded by

    saipavankumar.vemuri69
    5 views18 pages

    Original Title

    ASP UNIT-2 question bank

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    5 views18 pages

    ASP UNIT-2 Question Bank

    Uploaded by

    saipavankumar.vemuri69

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 18

    UNIT 2

    PART A
    1)What are different approaches of optimization of a linear discrete time
    filter?
    There are two approaches of optimization of a linear discrete time filter:
    1.Principle of Orthogonality approach
    2.Error Performance Surface approach
    2)State Principle of orthogonality.
    The necessary and sufficient condition for the cost function J to attain its
    minimum value is for the corresponding value of the estimation error eo(n) to
    be orthogonal to each input sample that enters into the estimation of the desired
    response at time n.

    3)Mention the significance of Wiener- Hopf equation.


    The system of equations defines the optimum filter coefficients, in the most
    general setting, in terms of two correlation functions: the autocorrelation
    function of the filter input and the cross-correlation between the filter input and
    the desired response.These equations are called the Wiener–Hopf equations.

    4)How is Error performance surface of an FIR filter characterized?

    Equation states that, for the case when the tap inputs of the FIR filter and
    the desired response are jointly stationary, the cost function, or mean-square
    error, J is precisely a second-order function of the tap weights in the filter.
    Consequently, we may visualize the dependence of J on the tap weights w0, w1,
    c, wM-1 as a bowl-shaped 1M + 12-dimensional surface with M degrees of
    freedom represented by the tap weights of the filter; it is 1M + 12-dimensional
    because we have the variance sd 2 plus the M tap weights which are all needed
    to fully describe the cost function J. This surface is characterized by a unique
    minimum. For obvious reasons, we refer to the surface so described as the error-
    performance surface of the FIR filter

    5)Justify that Steepest Descent method is a deterministic search method.


    6)Mention the distinctive features of LMS algorithm.

    7) Compare Localized Optimality of LMS algorithm and Stochastic


    Gradient Descent method.
    8) Mention the role of Learning curves.

    9) Define Misadjustment with respect to LMS algorithm.


    10) How does Rate of convergence of LMS algorithm depend on Step-size
    parameter?
    PART B

    1.Define the problem of Linear Optimum Filtering.


    2. Derive the Principle of orthogonality.
    3.Derive Wiener-Hopf equations and find its solution for FIR filters.
    5.How Newton’s method removes the limitation of Steepest Descent
    algorithm?
    6. Explain the principles of Stochastic Gradient Descent method.

    7. How is Stochastic Gradient Descent method applied in Least Mean


    Square (LMS) algorithm?
    8.Discuss different kinds of Learning curves.

    9. Explain Transient behavior and Convergence considerations of LMS


    algorithm.
    10. Deduce the relation of Misadjustment ?
    4. Explain Steepest Descent algorithm by finding corresponding
    mathematical equations.

    You might also like