Scribd Logo
Upload

Welcome to Scribd!

  • 2K views

    Clustering - The Data Ensemble Q&A

    Uploaded by

    Ramesh Darling
    The document contains questions about clustering algorithms and their properties. It tests knowledge about preferred distance measures, types of clustering like agglomerative and k-means, complexity measures like O(N^3), and validation techniques like cross validation. Key clustering concepts and algorithms like centroids, dendograms, convergence, and functions in R like hclust() are also assessed.

    Copyright:

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

    Clustering - The Data Ensemble Q&A

    Uploaded by

    Ramesh Darling
    2K views2 pages
    The document contains questions about clustering algorithms and their properties. It tests knowledge about preferred distance measures, types of clustering like agglomerative and k-means, complexity measures like O(N^3), and validation techniques like cross validation. Key clustering concepts and algorithms like centroids, dendograms, convergence, and functions in R like hclust() are also assessed.

    Original Title

    Clustering - The Data Ensemble Q&A.txt

    Copyright

    © © All Rights Reserved

    Available Formats

    TXT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document contains questions about clustering algorithms and their properties. It tests knowledge about preferred distance measures, types of clustering like agglomerative and k-means, complexity measures like O(N^3), and validation techniques like cross validation. Key clustering concepts and algorithms like centroids, dendograms, convergence, and functions in R like hclust() are also assessed.

    Copyright:

    © All Rights Reserved
    Download as TXT, PDF, TXT or read online from Scribd
    Download as txt, pdf, or txt
    2K views2 pages

    Clustering - The Data Ensemble Q&A

    Uploaded by

    Ramesh Darling
    The document contains questions about clustering algorithms and their properties. It tests knowledge about preferred distance measures, types of clustering like agglomerative and k-means, complexity measures like O(N^3), and validation techniques like cross validation. Key clustering concepts and algorithms like centroids, dendograms, convergence, and functions in R like hclust() are also assessed.

    Copyright:

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

    What is a preferred distance measure while dealing with sets ?

    Jaccard -- Correct

    Each point is a cluster in itself. We then combine the two nearest clusters into
    one. What type of clustering does this represent ?
    Agglomerative -- Correct

    Which learning is the method of finding structure in the data without labels.
    Unsupervised -- Correct

    ____________ of a set of points is defined using a distance measure .


    Similarity -- Correct

    Members of the same cluster are far away / distant from each other .
    False -- Correct

    Unsupervised learning focuses on understanding the data and its underlying pattern.
    True -- Correct

    ***********************************************************************************
    *****************************

    ___________ of two points is the average of the two points in Eucledian Space.
    Centroid -- Correct

    A centroid is a valid point in a non-Eucledian space .


    False -- Correct

    What is the overall complexity of the the Agglomerative Hierarchical Clustering ?


    O(N^3) -- Correct

    ___________ measures the goodness of a cluster


    Cohesion -- Correct

    ___________ is the data point that is closest to the other point in the cluster.
    Clusteroid -- Correct

    The ______ is a visual representation of how the data points are merged to form
    clusters.
    Dendogram -- Correct

    ***********************************************************************************
    *****************************

    _____________ is when points don't move between clusters and centroids stabilize.
    Convergence -- Correct

    ___________ is a way of finding the k value for k means clustering.


    Cross Validation -- Correct

    The number of rounds for convergence in k means clustering can be lage


    True -- Correct

    Sampling is one technique to pick the initial k points in K Means Clustering


    True -- Correct

    K Means algorithm assumes Eucledian Space/Distance


    True -- Correct
    ***********************************************************************************
    *****************************

    What is the R Function to divide a dataset into k clusters ?


    kclusters() -- Wrong

    What is the R function to apply hierarchical clustering to a matrix of distance


    objects ?
    hclust() -- Correct

    You might also like