Scribd Logo
Upload

Welcome to Scribd!

  • 4 views

    5 IntroML

    Uploaded by

    sdog444514
    This document introduces machine learning concepts including supervised vs unsupervised learning, regression vs classification, evaluation metrics, and scikit-learn library. It provides examples of supervised learning algorithms like decision trees and uses the iris flower dataset to demonstrate classification.

    Copyright:

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

    5 IntroML

    Uploaded by

    sdog444514
    4 views23 pages
    This document introduces machine learning concepts including supervised vs unsupervised learning, regression vs classification, evaluation metrics, and scikit-learn library. It provides examples of supervised learning algorithms like decision trees and uses the iris flower dataset to demonstrate classification.

    Original Title

    5_IntroML

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document introduces machine learning concepts including supervised vs unsupervised learning, regression vs classification, evaluation metrics, and scikit-learn library. It provides examples of supervised learning algorithms like decision trees and uses the iris flower dataset to demonstrate classification.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    4 views23 pages

    5 IntroML

    Uploaded by

    sdog444514
    This document introduces machine learning concepts including supervised vs unsupervised learning, regression vs classification, evaluation metrics, and scikit-learn library. It provides examples of supervised learning algorithms like decision trees and uses the iris flower dataset to demonstrate classification.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 23

    Introduction:

    Machine Learning
    Welcome to Machine Learning!

    Big Data, Machine Learning, and their Real World Applications


    Pre-College Program
    Columbia University, SPS
    Concepts
    • Types of Machine Learning
    • Supervised Learning
    • Regression vs Classification
    • Models vs Learning Algorithms
    • Scikit-learn library
    • Evaluation Metrics
    • Picking the best model
    What is Machine Learning?
    • “[Machine Learning is the] field of study that gives computers the
    ability to learn without being explicitly programmed.]” - Arthur
    Samuel , 1959
    What is Machine Learning?
    • “[Machine Learning is the] field of study that gives computers the
    ability to learn without being explicitly programmed.”

    • “A computer program is said to learn from experience E with respect


    to some task T and some performance measure P, if its performance on
    T, as measured by P, improves with experience E." -- Tom Mitchell,
    Carnegie Mellon University
    Types of Machine Learning
    Supervised vs Unsupervised Learning
    Supervised Learning
    Unsupervised
    Reinforcement Learning

    Alpha Go Trailer

    AlphaGo Zero

    https://medium.com/@evepardi
    /reinforcement-learning-in-gaming-583a42bc2a9b
    Inverse Reinforcement Learning- learning
    from Actions
    Examples: Supervised or Unsupervised?
    • Determining whether or not the user will click on the advertising
    banner based on website content and click history.
    • Dividing online market customers into groups based on their purchase
    history.
    • Identifying a user's age based on purchase history. You have access to
    the purchase history of the clients whose ages are known.
    Back to Supervised Learning
    More on Data
    Features vs Target Variables
    • Features are variables
    that help predict the
    target variable.
    • ML Algorithm takes in
    features and labels
    (input) to predict target
    variable (output).
    Feature vs Target Variables: Example
    (Housing Price)
    Regression vs Classification
    • Regression algorithms are used to predict the continuous values such
    as price, salary, age, etc.
    • Classification algorithms are used to predict/Classify the discrete
    values such as Male or Female, True or False, Spam or Not Spam, etc.
    Evaluation of Algorithms
    • Classification: How many labels did we predict correctly?
    • Accuracy – e.g. my model is 99% accurate
    • Precision, Recall, Specificity…. We will learn more about these later!
    • Regression: How far off are we from the continuous target variable?
    • Mean Squared Error (MSE)
    • Mean Absolute Error (MAE)
    Final Team Project Exercise
    1. For Both Data Analysis and Machine Learning Projects:
    Based on your ideas for a project, identify data that you might use .
    Kaggle.com has a collection of datasets that might help you.
    2. What are your features? What is your target variable? (If working on Data
    Analysis, please identify a possible ML problem with this data)
    3. Is this a Supervised Learning, Unsupervised Learning, or Reinforcement
    Learning problem?
    4. If Supervised, is this classification or regression?
    5. How will you evaluate this algorithm? Accuracy / Mean Squared Error?
    6. Start visualizing your data in Pandas (what are the columns, any quick graphs
    you can make to explore your data?)
    Algorithm Example: The Decision Tree
    (Classification)
    Algorithm Example- The Deicision Tree
    (Regressor)
    An Example: Classifying species of Iris
    flowers
    • Features:
    • Sepal length (cm)
    • Sepal width (cm)
    • Petal length (cm)
    • Petal width (cm)
    • Target
    • Class: 0,1,2 (species)
    Introduction to scikit-learn library

    https://machinelearningmastery.com
    /a-gentle-introduction-to-scikit-learn-a-python-machine-learnin
    g-library/

    You might also like