Scribd Logo
Upload

Welcome to Scribd!

  • 30 views

    ECE/Exam Cell/002 Vtu No.: School of Electrical & Communication Department of Ece

    Uploaded by

    immaikkaa nodigal
    This document contains a unit test for an Introduction to Machine Learning course. It provides data on patients affected or not affected by a disease based on 5 features. The test asks students to analyze the data and answer questions related to determining the relationship between features, converting the relationship to a linear model, identifying support vectors and maximum margin, determining the maximum margin hyperplane, converting the problem to multiclass, and suggesting methods to increase testing accuracy. It is worth 10 marks and assesses students' ability to apply concepts related to support vector machines.

    Copyright:

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

    ECE/Exam Cell/002 Vtu No.: School of Electrical & Communication Department of Ece

    Uploaded by

    immaikkaa nodigal
    30 views2 pages
    This document contains a unit test for an Introduction to Machine Learning course. It provides data on patients affected or not affected by a disease based on 5 features. The test asks students to analyze the data and answer questions related to determining the relationship between features, converting the relationship to a linear model, identifying support vectors and maximum margin, determining the maximum margin hyperplane, converting the problem to multiclass, and suggesting methods to increase testing accuracy. It is worth 10 marks and assesses students' ability to apply concepts related to support vector machines.

    Original Title

    OEQ-UT2-IML (2)

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document contains a unit test for an Introduction to Machine Learning course. It provides data on patients affected or not affected by a disease based on 5 features. The test asks students to analyze the data and answer questions related to determining the relationship between features, converting the relationship to a linear model, identifying support vectors and maximum margin, determining the maximum margin hyperplane, converting the problem to multiclass, and suggesting methods to increase testing accuracy. It is worth 10 marks and assesses students' ability to apply concepts related to support vector machines.

    Copyright:

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

    ECE/Exam Cell/002 Vtu No.: School of Electrical & Communication Department of Ece

    Uploaded by

    immaikkaa nodigal
    This document contains a unit test for an Introduction to Machine Learning course. It provides data on patients affected or not affected by a disease based on 5 features. The test asks students to analyze the data and answer questions related to determining the relationship between features, converting the relationship to a linear model, identifying support vectors and maximum margin, determining the maximum margin hyperplane, converting the problem to multiclass, and suggesting methods to increase testing accuracy. It is worth 10 marks and assesses students' ability to apply concepts related to support vector machines.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    You are on page 1of 2

    VTU No.

    ECE/Exam Cell/002
    Regular/Retest

    SCHOOL OF ELECTRICAL & COMMUNICATION


    DEPARTMENT OF ECE

    VTU R 2015

    UNIT TEST – II
    B.Tech. - ECE
    Course Category: Program Elective
    Course Code/Course Title: 1152EC154/Introduction to Machine Learning ````Max.Marks:10
    Semester: Even Semester Date of Exam:14.05.2020
    Achievable Course Outcomes
    CO3: Explain Support Vector Machine Concepts

    S.No. Answer the following Question Marks CO K Level


    1. The table below gives the data (normalized values) for persons affected/not
    affected with a particular type of disease. Analyze the data and answer the
    following questions.
    1. Find the relationship between the patients and features. Linear or
    nonlinear. (Hint: Consider all 5 features. Find if any
    interrelationship exists between certain features)
    2. If non linear, propose a technique to convert the relationship into
    a linear model.
    3. Plot the data given in X1 and X2 as a 2D plot and identify the
    strategy to define 2 classes.
    (Hint: From the X2 values select an appropriate value to
    represent the threshold)
    4. Determine the support vectors and maximum margin.
    5. Find the maximum margin hyperplane for the given problem. 10 CO3 K3
    6. Is it possible to convert the above problem to a multiclass
    problem? Explain
    7. Suggest methods to increase testing accuracy when training
    accuracy is high.

    Patien Features
    Y X1 X2 X3 X4 X5
    1 1.5 1.8 0.33 1.12 1
    2 7.2 0.9 0.81 25.9 5
    3 3.3 1.9 0.52 5.44 2
    4 4.5 2.5 0.7 10.1 3
    5 6 0.85 0.68 18 8
    6 4 0.75 0.47 8 9
    7 2.9 1.1 0.4 4.20 7
    8 5.5 3 0.85 15.1 4
    9 2.4 0.65 0.30 2.88 5
    10 9 2.6 1.16 40.5 6
    K1-Remember K2-Understand K3-Apply K4-Analyze K5-Evaluate K6-Create
    VTU No. ECE/Exam Cell/002
    Regular/Retest

    SCHOOL OF ELECTRICAL & COMMUNICATION


    DEPARTMENT OF ECE

    VTU R 2015
    Rubrics:

    1 General equation representing the data 2 marks


    2 Transformation to be used 1 marks
    3 Threshold for differentiating two classes 1 mark
    4 Support vector and maximum mar 1 mark
    5 Maximum hyperplane 3 marks
    6 Multiclass 1 mark
    7 Accuracy improvement method 1 mark

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy