Introductory Tutorials For Machine Learning


Introductory Tutorials For Machine Learning

Last updated on 2019-02-08

Machine learning is changing the way we engineer software. Tasks like parsing and summarizing text used to be done with thousands of lines of procedural code. Now they are done with neural networks containing millions of trained parameters. Whether you're a beginner or expert, some understanding of machine learning is now vital to being a software engineer.

Introductory tutorials provide a great place for a person to kickstart their machine learning journey. I recommend the tutorials in this book for somebody who is just starting machine learning career or wants to brush up their skills. A breadth of practical examples serve as a resource to people across domains and machine learning enthusiasts at any level. Written in simple English, technical concepts are explained in intuitive, easy-to-follow language.

Derrick Mwiti has been a valuable contributor to Heartbeat since we started the publication. He is incredibly generous in creating tutorials that support other developers. His passion for sharing machine learning knowledge can be seen in the care he has put into every page of this book. If you are looking for the best place to start your machine learning and data science career, I recommend that you start here.

Jameson Toole

Cofounder and CEO at Fritz

Boston, MA, USA

Foreword 3

Introduction 6

The State of Data Science and Machine Learning, Part 1: Education, job titles, and skills 7

What programming language should aspiring data scientists learn? 14

Thinking of blogging about Data Science? Here are some tips and possible benefits. 19

New to data science? Here are a few places to start 24

Data Visualization & Exploration using Pandas Only: Beginner 26

Introduction to Python Metaclasses 37

JSON Data in Python 44

Decorators in Python 52

Introduction to MongoDB and Python 61

Dash for Beginners 74

Introduction to Deep Learning with Keras 90

A Beginner’s Guide to Convolutional Neural Networks (CNN) 103

Guide to saving & hosting your first machine learning model 113

Introduction to Generative Adversarial Networks (GANs) 131

Introduction to Self-Organizing Maps (SOMs) 147

Introduction to Restricted Boltzmann Machines Using PyTorch 160

Boosting your Machine Learning Models Using XGBoost 172

Introduction to PyTorch for Deep Learning 179

How to Perform Neural Style Transfer with PyTorch 187

How to build a Simple Recommender System in Python 201

Detecting the Language of a Person’s Name using a PyTorch RNN 212

Using a Keras Long Short-Term Memory (LSTM) Model to Predict Stock Prices 224

Sales Forecasting Using Facebook’s Prophet 231

Automated Machine Learning in Python 240

Using Caret in R to Classify Term Deposit Subscriptions for a Bank 248

Object Detection with Luminoth 254

Handling Text Data with a Keras Embedding Layer 260

Within 45 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.

See full terms...