1st Edition

Machine Learning, Animated

By Mark Liu Copyright 2024
    464 Pages 45 Color Illustrations
    by Chapman & Hall

    496 Pages 45 Color Illustrations
    by Chapman & Hall

    Also available as eBook on:

    The release of ChatGPT has kicked off an arms race in Machine Learning (ML), however ML has also been described as a black box and very hard to understand. Machine Learning, Animated eases you into basic ML concepts and summarizes the learning process in three words: initialize, adjust and repeat. This is illustrated step by step with animation to show how machines learn: from initial parameter values to adjusting each step, to the final converged parameters and predictions.

    This book teaches readers to create their own neural networks with dense and convolutional layers, and use them to make binary and multi-category classifications. Readers will learn how to build deep learning game strategies and combine this with reinforcement learning, witnessing AI achieve super-human performance in Atari games such as Breakout, Space Invaders, Seaquest and Beam Rider.

    Written in a clear and concise style, illustrated with animations and images, this book is particularly appealing to readers with no background in computer science, mathematics or statistics.


    Access the book's repository at: https://github.com/markhliu/MLA

    List of Figures

    Preface

    Section I Installing Python and Learning Animations

     

    1. Installing Anaconda and Jupyter Notebook

     

    2. Creating Animations

     

    Section II Machine Learning Basics

     

    3. Machine Learning: An Overview

     

    4. Gradient Descent - Where the Magic Happens

     

    5. Introduction to Neural Networks

     

    6. Activation Functions

     

    Section III Binary and Multi-Category Classifications

     

    7. Binary Classifications

     

    8. Convolutional Neural Networks

     

    9. Multi-Category Image Classifications

     

    Section IV Developing Deep Learning Game Strategies

     

    10. Deep Learning Game Strategies

     

    11. Deep Learning in the Cart Pole Game

     

    12. Deep Learning in Multi-Player Games

     

    13. Deep Learning in Connect Four

     

    Section V Reinforcement Learning

     

    14. Introduction to Reinforcement Learning

     

    15. Q-Learning with Continuous States

     

    16. Solving Real-World Problems with Machine Learning

     

    Section VI Deep Reinforcement Learning

     

    17. Deep Q-Learning

     

    18. Policy-Based Deep Reinforcement Learning

     

    19. The Policy Gradient Method in Breakout

     

    20. Double Deep Q-Learning

     

    21. Space Invaders with Double Deep Q-Learning

     

    22. Scaling Up Double Deep Q-Learning

    Bibliography

    Biography

    Mark H. Liu is Associate Professor of Finance, (Founding) Director of MS Finance Program, University of Kentucky. Mark is currently the director of Master of Science in Finance program at the University of Kentucky, U.S.A. He is also an associate professor of finance with tenure at the University of Kentucky. He obtained his Ph.D. in finance from Boston College in 2004 and his M.A. in economics from Western University in Canada in 1998. His research interest is in machine learning and corporate finance. He has published his research in top finance journals such as Journal of Financial Economics, Journal of Financial and Quantitative Analysis, Journal of Corporate Finance, and Review of Corporate Finance Studies. Dr. Mark Liu has run Python workshops for master students at the University of Kentucky in the last few years. He has incorporated Python in his teaching. In particular, he is now teaching a Python Predictive Analytics course to graduate students. As the director of the MS Finance program, Mark has seen first-hand the high demand for machine learning skills in all industries. He has interacted with executives and recruiters from hundreds of companies, who in recent years have put an increasing emphasis on the importance of incorporating machine learning and data analytics skills in all business fields.