A Brief Challenge
Introduction
Hi, my name is Billy and I am setting out to read “Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems” by Aurelien Geron.
My Goal
I am proposing this challenge of reading one chapter a day to help keep myself engaged in a somewhat daunting book. The book is 19 chapters with about 750 pages of content. I am hoping to finish the entire book in 19 days but realistically I am giving myself 21 days to read it in it’s entirety. This is not an obscene goal by any standard but I am hoping to read this book quickly but not so quickly that I don’t absorb the content.
While reading this book I am hoping to strengthen my understanding of machine learning and the algorithms that power it. I am excited to dive a bit more into the math and nitty gritty of the methods I have previously touched on in an applied manner to strengthen my understanding and future application of those methods.
Lastly, I am currently a few days ahead in my readings which will hopefully allow me to keep up with blog posts (ie: Read the chapter one day and then reflect & blog the next day). This will also hopefully increase my retention rates.
My Background:
I am not a ML Engineer or a Data Scientist but rather a Devops Engineer on a learning journey. I have an intermediate understanding of Python and its data science libraries such as Pandas, NumPy, SkLearn, and Matplotlib. Before reading this book I completed the Applied Data Science with Python Specialization through UMSI & Coursera (review forthcoming but I highly recommend) and am currently also enrolled in IBM’s Advanced Data Science Specialization. I also have completed FreeCodeCamp.org’s Machine Learning with Python course which gave me an introductory background in Tensorflow 2 and neural networks.
In college I majored in Economics and Minored in Computer Science from a relatively average college and did not take any Machine Learning Courses.
Prerequisites:
I highly recommend that you have at least an intermediate understanding of python including concepts like lambdas and comprehensions and in data science oriented libraries like Pandas, NumPy, and Matplotlib. If you don’t have these I recommend Harvards CS50, Dr. Chuck’s Python for Everybody (Free in some places paid in others), and UMSI’s Applied Data Science with Python Specialization referenced above.
In terms of a mathematical background you should have a foundational knowledge in Probability, Statistics, Calculus, and Linear Algebra. If you do not have these or need a refresher there are many ways to learn these (both free and paid) including MIT opencourseware, Harvard opencourseware, MOOC’s such as Udacity and Coursera, Youtube Channels (such as 3Blue1Brown), and many more!
Thanks for reading!
If you have any questions please reach out to me on twitter @wtothdev.
Disclaimer: I don’t make any money from any of the services referenced and chose to read and review this book under my own free will.
