Scribd Logo
Upload

Welcome to Scribd!

  • Neural Networks Exam

    Uploaded by

    fruit1991
    338 views3 pages
    The document is a past exam paper for a neural networks and fuzzy control course. It contains 6 questions testing knowledge of various neural network and fuzzy logic concepts. The questions cover topics such as: comparing artificial and biological neural networks; training networks using the Widrow-Hoff learning rule; realizing the exclusive-or function with a McCulloch-Pitts neuron; explaining the MADALINE algorithm; storing input-output patterns using the Hebb rule; and more. Students are instructed to answer 5 of the 6 questions, each worth 20 marks, for a total exam mark of 100.

    Original Description:

    exam

    Original Title

    neural networks exam

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    The document is a past exam paper for a neural networks and fuzzy control course. It contains 6 questions testing knowledge of various neural network and fuzzy logic concepts. The questions cover topics such as: comparing artificial and biological neural networks; training networks using the Widrow-Hoff learning rule; realizing the exclusive-or function with a McCulloch-Pitts neuron; explaining the MADALINE algorithm; storing input-output patterns using the Hebb rule; and more. Students are instructed to answer 5 of the 6 questions, each worth 20 marks, for a total exam mark of 100.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pdf or txt
    338 views3 pages

    Neural Networks Exam

    Uploaded by

    fruit1991
    The document is a past exam paper for a neural networks and fuzzy control course. It contains 6 questions testing knowledge of various neural network and fuzzy logic concepts. The questions cover topics such as: comparing artificial and biological neural networks; training networks using the Widrow-Hoff learning rule; realizing the exclusive-or function with a McCulloch-Pitts neuron; explaining the MADALINE algorithm; storing input-output patterns using the Hebb rule; and more. Students are instructed to answer 5 of the 6 questions, each worth 20 marks, for a total exam mark of 100.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pdf or txt
    of 3

    Term End Examination - November 2011

    Course :
    Time

    EEE408 - Neural Networks and Fuzzy Control

    : Three Hours

    Slot: G2
    Max.Marks:100

    Answer any FIVE Questions


    (5 X 20 = 100 Marks)
    1.

    a)

    List the comparison between artificial and biological neural network.

    [5]

    b)

    Perform two training steps for the network with learning constant c=0.25 using the

    [5]

    following inputs. Train the network using Widrow-Hoff learning rule.

    2
    1

    X1 = 0 , d1 = 1 ; X 2 = 2, d 2 = 1 . Find the final weights for bipolar continuous


    1
    1
    f(net) and bipolar continuous neurons f(net), =1. The initial weight is [1 0 1]t.

    2.

    c)

    Realize the Exclusive-OR function using Mccolloch-Pitts neuron.

    [10]

    a)

    With neat architecture, explain the MADALINE algorithm.

    [10]

    b)

    Find the weight matrix to store the following input output patterns using Hebb

    [10]

    rule.

    A1=[1 0 1]; B1=[1 0]


    A2=[0 1 0]; B2=[0 1].

    (i) Using the binary step function (with target 0) as the activation function for both
    layers, test the response of your network in both directions of each binary training
    pattern. Initial activation of the other layers is set to zero
    (ii) Using the bipolar step function (with target 0) as the activation function for both
    layers. Convert the training patterns to bipolar form and test the network response
    in both directions again. Initial activation is as in part(i).
    (iii) Test the response of your network on each of the following noisy versions of the
    bipolar form of the training patterns.[0 -1 1],[0 0 1]&[-1 0 -1].

    3.

    a)

    Draw and explain the architecture of Maxnet and Hamming net with necessary
    equations.
    Page 1 of 3

    [10]

    b)

    The four-dimensional vectors assigned to two classes. The four vectors and associated

    [10]

    classes are
    Vector

    Class

    [1,0,1,0]

    [0,0,1,1]

    [1,1,0,0]

    [1,0,0,1]

    To initialize the network weights use the first two input vectors.

    Initialize the

    learning rate parameter to 0.1. Perform one epoch of training using LVQ algorithm.
    Also draw the neural architecture of this LVQ and indicate the weights obtained after
    one training epoch.

    4.

    a)

    Use the Hebb rule to store the vectors [1, 1, 1, 1] and [1, 1, -1, -1] in an autoassociative

    [10]

    neural net.
    (i)Find the weight matrix. (Do not set diagonal terms set to zero.)
    (ii)Test the net, using the vector [1, 1, 1, 1] as input.
    (iii)Test the net, using [1, 1, -1, -1] as input.
    (iv)Test the net, using [1, 1, 1, 0]
    b)

    Design a Hopfield network to store [1 1 1 1], [-1 1 -1 1]. Test the performance of the

    [10]

    network with input vectors. [-1 1 -1 -1], [1 -1 1 1] using synchronized and


    asynchronized updation. Also find the variation of energy for input [-1 1 -1 -1]

    5.

    a)

    Explain the training algorithm used in self organizing feature maps with neat

    [10]

    architecture.
    b)

    For the given exemplar vectors e(1)=[-1 1 1 1] and e(2)=[1 -1 1 -1], use Hamming net
    to find the exemplar that is closest to each of the bipolar input patterns. The input
    patterns are [1 1 -1 -1],[-1 1 1 -1],[-1 -1 -1 -1], [-1 -1 1 1] and assume the initial weight
    0 .5 0 .5 0 .5 0 .5
    matrix as

    0 .5 0 .5 0 .5 0 .5

    Page 2 of 3

    [10]

    6.

    a)

    Write the properties of classical sets.

    [5]

    b)

    The fuzzy sets A and B are given by

    [5]

    1 0 .5 0 .3 0 .2
    0 .5 0 .7 0 .2 0 .4
    A= +
    +
    +
    +
    +
    +
    and B =
    .
    4
    5
    3
    4
    5
    2 3
    2
    Find
    ( i ) A B (ii) A B (iii) Complement of A and B.
    c)

    Explain the different methods of defuzzification with neat diagram.

    [10]

    Page 3 of 3

    You might also like