Scribd Logo
Upload

Welcome to Scribd!

  • 11 views

    CPE412 Pattern Recognition (Week 2)

    Uploaded by

    Basil Albattah
    The document discusses feature formation and feature selection in machine learning. It covers supervised learning where categories are provided, unsupervised learning which forms clusters without categories, and reinforcement learning which gets feedback on decisions. The document outlines the machine learning process including data acquisition, pre-processing, feature extraction, classification, and post-processing. It defines features as object properties that represent classes, are compact, efficient to compute, and perceptually relevant. Decision processes and feature selection methods are also briefly covered.

    Copyright:

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

    CPE412 Pattern Recognition (Week 2)

    Uploaded by

    Basil Albattah
    11 views28 pages
    The document discusses feature formation and feature selection in machine learning. It covers supervised learning where categories are provided, unsupervised learning which forms clusters without categories, and reinforcement learning which gets feedback on decisions. The document outlines the machine learning process including data acquisition, pre-processing, feature extraction, classification, and post-processing. It defines features as object properties that represent classes, are compact, efficient to compute, and perceptually relevant. Decision processes and feature selection methods are also briefly covered.

    Original Title

    CPE412 Pattern Recognition(week 2)

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses feature formation and feature selection in machine learning. It covers supervised learning where categories are provided, unsupervised learning which forms clusters without categories, and reinforcement learning which gets feedback on decisions. The document outlines the machine learning process including data acquisition, pre-processing, feature extraction, classification, and post-processing. It defines features as object properties that represent classes, are compact, efficient to compute, and perceptually relevant. Decision processes and feature selection methods are also briefly covered.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    11 views28 pages

    CPE412 Pattern Recognition (Week 2)

    Uploaded by

    Basil Albattah
    The document discusses feature formation and feature selection in machine learning. It covers supervised learning where categories are provided, unsupervised learning which forms clusters without categories, and reinforcement learning which gets feedback on decisions. The document outlines the machine learning process including data acquisition, pre-processing, feature extraction, classification, and post-processing. It defines features as object properties that represent classes, are compact, efficient to compute, and perceptually relevant. Decision processes and feature selection methods are also briefly covered.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 28

    Week 2

    Feature Formation and


    Feature Selection
    Dr. Nehad Ramaha,
    Computer Engineering Department
    Karabük Universities 1
    The class notes are a compilation and edition from many sources. The instructor does not claim intellectual property or ownership of the lecture notes.
     How can a machine learn the rule from data?
     Supervised learning: a teacher provides a category
    label or cost for each pattern in the training set.
    ◦ Classification
     Unsupervised learning: the system forms clusters or
    natural groupings of the input patterns (based on
    some similarity criteria).
    ◦ Clustering
     Reinforcement learning: no desired category is given
    but the teacher provides feedback to the system such
    as the decision is right or wrong.

    2
    3
    4
     Data acquisition and sensing:
    ◦ Measurements of physical variables.
    ◦ Important issues: bandwidth, resolution , etc.
     Pre-processing:
    ◦ Removal of noise in data.
    ◦ Isolation of patterns of interest from the
    background.
     Feature extraction:
    ◦ Finding a new representation in terms of features.
     Classification
    ◦ Using features and learned models to assign a
    pattern to a category.
     Post-processing
    ◦ Evaluation of confidence in decisions.

    5
     Features are properties of an object:
    ◦ Ideally representative of a specific type (i.e. class) of
    objects
    ◦ Compact (memory efficient)
    ◦ Computationally simple (CPU efficient)
    ◦ Perceptual relevant (if trying to implement a human
    inspired classifier)

    6
    7
    8
    9
    10
    11
    12
    13
    Decision process

    14
    15
    28

    You might also like