Scribd Logo
Upload

Welcome to Scribd!

  • Logistic Regression

    Uploaded by

    TayCK
    12 views8 pages
    This document discusses logistic regression, including its hypothesis representation using a sigmoid function, cost function to capture how close predictions are to the true labels, using gradient descent to minimize the cost function, handling multi-class classification by doing binary classification multiple times, overfitting and solutions like reducing features, regularization which keeps all features but reduces parameter magnitude, and how regularization is implemented for both linear and logistic regression by adjusting the cost function and gradient descent calculations.

    Original Description:

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    This document discusses logistic regression, including its hypothesis representation using a sigmoid function, cost function to capture how close predictions are to the true labels, using gradient descent to minimize the cost function, handling multi-class classification by doing binary classification multiple times, overfitting and solutions like reducing features, regularization which keeps all features but reduces parameter magnitude, and how regularization is implemented for both linear and logistic regression by adjusting the cost function and gradient descent calculations.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    12 views8 pages

    Logistic Regression

    Uploaded by

    TayCK
    This document discusses logistic regression, including its hypothesis representation using a sigmoid function, cost function to capture how close predictions are to the true labels, using gradient descent to minimize the cost function, handling multi-class classification by doing binary classification multiple times, overfitting and solutions like reducing features, regularization which keeps all features but reduces parameter magnitude, and how regularization is implemented for both linear and logistic regression by adjusting the cost function and gradient descent calculations.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    of 8

    Logistic Regression

    用sigmoid function

    Hypothesis Representation
    ttte.PNG

    Cost Function
    Capture.PNG

    Gradient Descendant
    Capture.PNG

    MultiClass Classification
    假设K个class
    对每一个class进行分类，总共做K次

    Overfitting
    Solution

    1. Reduce the number of features:


    Manually select which features to keep.
    Use a model selection algorithm (studied later in the course).
    2. Regularization
    Keep all the features, but reduce the magnitude of parameters θ(j)
    Regularization works well when we have a lot of slightly useful features.

    Regulariation(Linear Regression)
    Cost function

    在后面加一个降低theta的算式
    Capture.PNG

    Gradient Descent

    Capture.PNG
    Normal Equation

    Capture.PNG
    Regulariation(Logistics Regresion)
    Cost function

    Capture.PNG

    Gradient Descent

    Capture.PNG

    You might also like