memory based reasoning

Upload: bharti-sharma

Post on 03-Apr-2018

222 views

Category:

Documents


0 download

TRANSCRIPT

  • 7/28/2019 Memory Based Reasoning

    1/12

    PREPARED BY:

    ASHUTOSH KUMAR

    (00316204411)

    BHARTI SHARMA

    (00716204411)

    MEMORY BASED REASONING

  • 7/28/2019 Memory Based Reasoning

    2/12

    WHAT IS MBR?

    MBR stands forMemory Based Reason ing.

    In Memory Based Reasoning results are based

    on analogous situations in the past.

    Our ability to reason from experience dependson our ability to recognize appropriate

    examples from the past.

    These examples can be of: Movies, Food ,

    Traff ic patterns and rou tes.

    We identify similar example(s) and apply what

    we know/learned to current situation.

  • 7/28/2019 Memory Based Reasoning

    3/12

    These similar examples in MBR are referred to as

    Neighbors.

    Identifying similar cases from experience.

    Applying the information from these cases to the

    problem at hand.

    MBR finds neighbors similar to a new record anduses the neighbors for classification and

    prediction.

    By following all these basic information about

    MBR, we came to know that basically it means

    taking decisions for future depending on the past

    experiences.

  • 7/28/2019 Memory Based Reasoning

    4/12

    MBR uses known instances of a model to predict

    unknown instances.

    This data mining technique maintains a dataset ofknown records.

  • 7/28/2019 Memory Based Reasoning

    5/12

    MEMORY BASED REASONING ALGORITHM:

    This algorithm works on the principle in which firstwe identify similar instances in the past, then we

    use the past instances and apply the information

    about those instances to the present.

    The algorithm knows the characteristics of the

    records in this training dataset.

    When a new record arrives for evaluation, the

    algorithm finds similar to the new record then

    uses the characteristics of the neighbor for

    prediction and classification.

  • 7/28/2019 Memory Based Reasoning

    6/12

    When a new record arrives at the data mining tool,

    first the tool calculates the distance between this

    record and the records in the training dataset.

    The results determine which data records in the

    training dataset qualify to be considered as

    neighbors to the incoming data record.

    Next, the algorithm uses a combination function tocombine the results of the various distance functions

    to obtain final answer.

  • 7/28/2019 Memory Based Reasoning

    7/12

    TWO BASIC OPERATIONS OF MBR ALGORITHM:

    Distance function : assigns a distance between

    any two records.

    Combination function : combines the results fromthe neighbors to arrive at an answer

  • 7/28/2019 Memory Based Reasoning

    8/12

    APPLICATIONS OF MBR:

    Fraud detection.

    Customer response prediction.

    Medical treatments.

    Classifying responses MBR can process free-

    text responses and assign codes.

  • 7/28/2019 Memory Based Reasoning

    9/12

    STRENGTHS OF MBR:

    It produces results that are readilyunderstandable.

    It is applicable to arbitrary data types,

    even non-relational data. It works efficiently on almost any

    number of fields.

    Maintaining the training set requires aminimal amount of effort.

  • 7/28/2019 Memory Based Reasoning

    10/12

    The three main issues in solving a problem with MBR:

    Selecting the most suitable historical recordsto form the training or base dataset.

    Establishing the best way to compose the

    historical record. Determining the two essential functions,

    namely, the distance function and the

    combination function.

  • 7/28/2019 Memory Based Reasoning

    11/12

    Weaknesses of Memory-Based Reasoning:

    It is computationally expensive when doingclassification and prediction.

    It requires a large amount of storage for the

    training set.Results can be dependent on the choice of

    distance function, combination function, and

    number of neighbors.

  • 7/28/2019 Memory Based Reasoning

    12/12

    THANK YOU