Books

This machine learning book series aims at providing real hands-on training from general concepts and architecture to low-level details and mathematics. The first epoch covers the simplest linear associative network, proposes a brick notation for algebraic expressions, shows required calculus derivations, and illustrates gradient descent.

Google engineers are regular expression masters. Do you want to become one, too? The Smartest Way to Learn Python Regex transforms you into a regular expression master. The book leverages an innovative learning approach: (1) read a chapter, (2) watch a course video, and (3) solve a code puzzle. It's fun!

In Errors of Regression Models you’ll learn how to choose the most appropriate statistics to measure the accuracy of your regression-based prediction model.Written in plain English with no technical jargon, Errors of Regression Models is perfect for beginners!Discover how to measure the accuracy of your regression models quickly and effectively.

Welcome to one of the On Weekend Series, this series helped me a lot before, and I hope it helps you now. And this book is about the techniques that you should learn to learn, understand and bulid a convolution neural network. I hope you find what you need in this book.

Need to collect terabytes of data across all aspects of your operations? Need to transform complex scientific datasets into innovative software that is deployed across the pipeline, accelerating the pace and quality of all business decisions to unbelievable levels? Having problems with performance or maintenance? If so, this book is for you!

These three-volume book series cover a wide variety of topics in machine learning focusing on supervised and unsupervised learning, intended for data scientist and machine learning experts providing a very concise description of the scikit-learn library. The first volume covers the generalized linear models (linear & logistic regression).

A journey to discover how to change our constraints into competitive advantages for the @NewDataEra

Readers will learn discrete mathematical abstracts as well as its implementation in algorithm and data structures shown in various programming languages, such as C, C++, PHP, Java, C#, Python and Dart. This book combines two major components of Mathematics and Computer Science under one roof.

This book is designed to give you a comprehensive view of cloud computing including Big Data and Machine Learning. Many resources will be used including interactive labs on Cloud Platforms (Google, AWS, Azure) using Python. This is a project-based book with extensive hands-on assignments. Based on material taught at leading universities.

Python has grown in recent years, due to trends of data science and ML, and I think the main reason is because it’s essentially for a person to keep track of everything that is going on. And it makes “introducing” people to Python an interesting. Nowadays, audiences need to learn python in fast way for data science and that what we will give them.

En el manual expongo, de forma clara y sencilla, los conceptos básicos de un análisis exploratorio de datos a nivel descriptivo y cómo llevarlo a la práctica con el software estadístico R y datos reales. El libro está pensado para que el lector avance paso a paso en su proceso de auto-aprendizaje, por lo que se proporcionan muchos ejemplos.

tldr: Don't read this if all you want is from tensroflow import keras

With the rise of Data Science and Machine Learning, Data Engineering is quickly becoming a in-demand skill. Data Engineering requires a unique skillset that is hard to learn without experience. I will teach you how to write scalable data pipelines and more!

Learn how to analyze big datasets in a distributed environment without being bogged down by theoretical topics. The API is vast and other learning tools make the mistake of trying to cover everything. This book only covers what you need to know, so you can explore other parts of the API on your own!