Free AI and Robotics Books

Immerse yourself in Dive into Deep Learning, an engaging and accessible resource. Tailored for engineers, scientists, and students, it strikes a perfect balance between simplicity and technical rigor. You don’t need prior machine learning expertise; every concept is introduced anew. The appendix offers a math refresher, while practical runnable code instances foster intuitive understanding. Experience deep learning’s potential firsthand as you engage with this reader-friendly guide. …

In Robotic Process Automation Succinctly, author Ed Freitas will show readers how to use nonproprietary and open-source software to write RPA scripts using Python and some RPA techniques to automate some common and repetitive business tasks. …

In Neural Networks with JavaScript Succinctly, Author James McCaffrey leads you through the fundamental concepts of neural networks, including their architecture, input-output, tanh and softmax activation, back-propagation, error and accuracy, normalization and encoding, and model interpretation. …

Much of the data available today is unstructured and text-heavy, making it challenging for analysts to apply their usual data wrangling and visualization tools. With this practical book Text Mining with R, you’ll explore text-mining techniques with tidytext, a package that authors Julia Silge and David Robinson developed using the tidy principles behind R packages like ggraph and dplyr. You’ll learn how tidytext and other tidy tools in R can make text analysis easier and more effective. …

Neural networks are a powerful tool for developers, but harnessing them can be a challenge. With Keras Succinctly, author James McCaffrey introduces Keras, an open-source, neural network library designed specifically to make working with backend neural network tools easier. …

The purpose of this free online book, Neural Networks and Deep Learning is to help you master the core concepts of neural networks, including modern techniques for deep learning. After working through the book you will have written code that uses neural networks and deep learning to solve complex pattern recognition problems. And you will have a foundation to use neural networks and deep learning to attack problems of your own devising. …

Support Vector Machines (SVMs) are some of the most performant off-the-shelf, supervised machine-learning algorithms. In Support Vector Machines Succinctly, author Alexandre Kowalczyk guides readers through the building blocks of SVMs, from basic concepts to crucial problem-solving algorithms. He also includes numerous code examples and a lengthy bibliography for further study. By the end of the book, SVMs should be an important tool in the reader’s machine-learning toolbox. …

Neural Network Design (2nd Edition), by the authors of the Neural Network Toolbox for MATLAB, provides a clear and detailed coverage of fundamental neural network architectures and learning rules. This book gives an introduction to basic neural network architectures and learning rules. Emphasis is placed on the mathematical analysis of these networks, on methods of training them and on their application to practical engineering problems in such areas as nonlinear regression, pattern recognition, signal processing, data mining and control systems. …

What You Need to Know about Machine Learning: Leveraging data for future telling and data analysis is designed to act as a brief, practical introduction to machine learning. It is full of practical examples which will get you up a running quickly with the core tasks of machine learning. It will give you a greater understanding of the key basics of machine learning so that you have a good idea of how to advance after you’ve read the guide. …