Scribd Logo
Upload

Welcome to Scribd!

  • 12 views

    AI

    Uploaded by

    nunuarbib
    This document provides an overview of the key topics covered in a machine learning course. It discusses regression models, linear regression, gradient descent, classification with logistic regression, neural networks, activation functions, optimization techniques like Adam, and multiple classification. The document also touches on overfitting and practical advice for applying machine learning.

    Copyright:

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

    AI

    Uploaded by

    nunuarbib
    12 views24 pages
    This document provides an overview of the key topics covered in a machine learning course. It discusses regression models, linear regression, gradient descent, classification with logistic regression, neural networks, activation functions, optimization techniques like Adam, and multiple classification. The document also touches on overfitting and practical advice for applying machine learning.

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document provides an overview of the key topics covered in a machine learning course. It discusses regression models, linear regression, gradient descent, classification with logistic regression, neural networks, activation functions, optimization techniques like Adam, and multiple classification. The document also touches on overfitting and practical advice for applying machine learning.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    12 views24 pages

    AI

    Uploaded by

    nunuarbib
    This document provides an overview of the key topics covered in a machine learning course. It discusses regression models, linear regression, gradient descent, classification with logistic regression, neural networks, activation functions, optimization techniques like Adam, and multiple classification. The document also touches on overfitting and practical advice for applying machine learning.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 24

    Week 1- Regression model

    Size in feet Price in 1000$


    cost function -

    features : 6'8 13931)


    targets -

    Y f b)
    modele : W, b(X) =
    Wx + b = Y
    J(w ,
    es
    W, b :
    Parameters piessa

    scid/II
    M
    "
    ↑ = f( b (xi)
    ,
    =
    wx
    i
    + b 5(w)
    =
    2f

    ↳ 5(w , b) : Bl
    find W, b :

    Til is close to
    "
    for all (x' , y")
    -
    Isi De & 1508 Siddd
    5 cs18D (i) Y'13d) 199 21396
    training piced , ,

    data(X , y)

    L
    cost function :
    squared error cost function
    46 +(1 , 199

    M
    e

    J(w b)
    -

    Ifm& -i <

    3
    number of
    ·
    M
    , =

    training examples

    F-fu
    >

    J(w b) z
    ,
    =

    m
    & (f w, b(x"-yi))

    in math -

    minimize J (w , b)
    er
    , b
    Week 1- Train the model with gradient descent
    Week 2- multiple liner regression
    Week 2- practical
    Week 2- practical
    Week 3- classification with logistic regression
    Week 3- cost function for logistic regression
    Week 3- cost function for logistic regression
    Week 3- Gradient Descent Implementation
    Week 3- The problem of overfitting
    Course 2-

    Week 1- neural networks


    Week1- neural network layer
    Inference in code
    Week 2- Activation Functions
    Week 2- Advanced optimisation

    Model.compile(optimiser=tf.keras.optimizer.Adam(learning_rate=le-3)
    Week 2-Multiple Classification
    Week 2-Multiple Classification
    Week 3- Advice for applying machine learning

    You might also like