Machine Learning Mastery with Python: Understand Your Data, Create Accurate Models, and Work Projects End-to-End

id: 417124 not VIP Open in MaM

By Jason Brownlee

Series: Machine Learning Mastery

Language: English

Category: Ebook - Computer/Internet

Categories: Computer/Internet

Size: 2.4 MiB pdf Files: 1

Uploader: ad3f

Uploaded At: 2018-02-05 19:17:22

machine, learning, python

Description

You must understand algorithms to get good at machine learning.

The problem is that they are only ever explained using Math. No longer.

In this mega Ebook written in the friendly Machine Learning Mastery style that you’re used to, finally cut through the math and learn exactly how machine learning algorithms work.

Using clear explanations, simple pure Python code (no libraries!) and step-by-step tutorials you will discover how to load and prepare data, evaluate model skill, and implement a suite of linear, nonlinear and ensemble machine learning algorithms from scratch.

You Learn Best By Implementing Algorithms From Scratch
…But You Need Help With The First Step
Developers Learn Best By Trying Things Out…
If you’re like me, you don’t really understand something until you can implement it from scratch.

You need to understand each piece before you can understand the whole thing.

The same applies to machine learning algorithms.

You won’t feel like you really understand machine learning algorithms until you can put them together yourself.

Without the tools and fancy libraries.

Math Can Really Slow You Down…
The problem is, machine learning algorithms are only ever described using math.

It’s all Greek letters, it’s a pain to read and understand and this can really sap your motivation.

You simply don’t have the time to study 4 years of advanced math just to implement some algorithms.

You don’t need a degree in computer science to implement bubble sort and understand how it works. You just read a simple explanation and implement it in a few lines of code.

Why can’t implementing machine learning algorithms be the same?
(it can!)

You Need Clear Step-By-Step Tutorials…
What is missing is a set of step-by-step tutorials that lay it all out.

You don’t need to know the mathematical reason why machine learning algorithms work. You need a clear explanation of how they work so you can turn that into code.

You need each step of the learning and prediction spelled out super simple so you can write a small function that does the same thing and write a little test to confirm it works.

It’s the same way we learn anything when programming. Piece-by-piece.

Put a few of these pieces together and you have a world-class machine learning algorithm.

Introducing: “Machine Learning Algorithms From Scratch“
This is the book that I wish I had when starting out.

It is designed for exactly the way developers like you learn.

The book works through how to write small functions to load data and prepare it for learning.

There are tutorials on how to evaluate predictions and evaluate the performance of machine learning models.

Then there’s a suite of tutorials on how to implement linear, nonlinear and even ensemble machine learning algorithms from scratch.

Each tutorial is written in Python. This is the growing and soon to be the dominant programming language for applied machine learning and data science.
Each tutorial uses the standard library. There is no NumPy, no SciPy, no Scikit-Learn and no other advanced libraries to hide the details.
Each tutorial is standalone. Everything you need to understand and run an algorithm is right there, no flipping back and forth through the book to piece it together yourself.
Each tutorial is super simple. Code does not use fancy Python tricks that are hard to read and even harder to understand. I’ve opted for simple loops and the simplest data structures to help even Python novices see exactly what is going on.
Each tutorial actually works. Each function is added one at a time with full explanation and spot testing. Nothing is sprung on you and all the code works with sample output for you to compare to.

Other Torrents