Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 7 views

    Slides ML Ch1

    Uploaded by

    pangedarelle

    Copyright:

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

    Slides ML Ch1

    Uploaded by

    pangedarelle
    7 views11 pages

    Original Title

    Slides_ML_Ch1

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    7 views11 pages

    Slides ML Ch1

    Uploaded by

    pangedarelle

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 11

    Machine Learning

    Prof. Dr.-Ing. Maria Schweigel

    Machine Learning – Prof. Dr.-Ing. Maria Schweigel 1


    organizational things 2

    The Module in divided in a theoretical and a practical part.


    In first part of semester lessons will give you theoretical background.
    In the second part of semester the practical part starts. Therefor have a look to practical
    training guide and solve the tasks. We work with the open source SW Tensorflow which have to
    be installed on your computer. We use our meetings to discuss about problems and results of
    your tasks. You have the possibility to work on your own ML project. With a presentation of
    your project you can earn some extra points for written exam. Please consider that each
    student have to work on an own project.

    Course consists of :
    • Theoritical basics: Lectures and Exercises
    • Practical part: examples and ML-project
    Materials on studip:
    • Slides of lesson
    • Practical training guide for practical part
    Meetings:
    • First part of semester theoretical basics
    • Second part of semester for consultation and disscussion about practical part
    • presentations of students projects at the end of semester
    Exam:
    • Exam preparation at one of the last meetings
    • written exam at end of semester about 120 min

    Machine Learning – Prof. Dr.-Ing. Maria Schweigel


    literature 3

    In libray available:

    • Machine Learning Algorithms : Popular Algorithms for Data Science and Machine Learning,
    Bonaccorso, Giuseppe

    • Machine learning for dummies / by John Paul Mueller and Luca Massaron

    • Fundamentals of machine learning for predictive data analytics : algorithms, worked examples, and case
    studies / John D. Kelleher, Brian Mac Namee, Aoife D'Arcy

    • Hands-On Neural Networks with TensorFlow 2. 0 : Understand TensorFlow, from Static Graph to Eager
    Execution, and Design Neural Networks, Galeone, Paolo

    • Hands-On Ensemble Learning with Python : Build Highly Optimized Ensemble Machine Learning Models
    Using Scikit-Learn and Keras, Kyriakides, George

    • Maschinelles Lernen , Alpaydın, Ethem

    • Machine Learning kompakt : alles, was Sie wissen müssen / Andriy Burkov ; Übersetzung aus dem
    Amerikanischen von Knut Lorenzen

    Ebooks:
    • An Introduction to Machine Learning, Miroslav Kubat, © Springer International Publishing, ISBN 978-3-
    319-63912-3 ISBN 978-3-319-63913-0 (eBook)

    Machine Learning – Prof. Dr.-Ing. Maria Schweigel


    content 4

    1. Introduction to Machine Learning


    History of ML, Terms of ML, Learning process,
    Applications of ML, Key problems of ML
    2. Algorithms used for ML
    Decision Trees, Probabilistic Networks (Bayesian),
    Nearest-Neighbor Classifiers, Neural network
    (NN), Support Vector Machine (SVM)
    3. Methods of Machine Learning
    Supervised learning, Unsupervised learning,
    Reinforcement learning
    4. Data Science and ML
    Needed data sets, Examples of data sets,
    Problems with data
    Machine Learning – Prof. Dr.-Ing. Maria Schweigel
    Content (2) 5

    5. Quality values of ML-Algorithms


    error rate and accuracy, Confusion matrix for 2-
    class problems, other two class quality values,
    Confusion matrix for m-class problems, Mean
    Square Error
    6. Parameter optimization
    gradient method, Backpropagation, Over- and
    underfitting, Grid searching, Genetic algorithms
    7. Tensor Flow for ML
    What is TensorFlow?, Keras - The high-level API
    for TensorFlow, Support Vector Machine in
    Tensorflow
    Machine Learning – Prof. Dr.-Ing. Maria Schweigel
    6

    Introduction to
    Machine learning

    Machine Learning – Prof. Dr.-Ing. Maria Schweigel


    First ML example 7

    Is the matermelon ripe?


    Introduction

    Machine Learning – Prof. Dr.-Ing. Maria Schweigel


    Definition ML 8

    Many definitions exist! One possible:

    “Machine learning is the technique that


    Introduction

    improves system performance by learning from


    experience via computational methods.”

    Machine Learning – Prof. Dr.-Ing. Maria Schweigel


    First ML example 9

    4 samples of our ML example:


    Introduction

    Zhou, Machine Learning,2021

    Machine Learning – Prof. Dr.-Ing. Maria Schweigel


    Example Character recognition 10

    From 6x4 images with handwritten character


    (number or letter)
    Introduction

    Kubat, An Introduction to Machine Learning,2017

    Machine Learning – Prof. Dr.-Ing. Maria Schweigel


    Learning process 11

    Find correct process flow by sort single steps!


    Introduction

    Machine Learning – Prof. Dr.-Ing. Maria Schweigel

    You might also like