Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple acc...
This book covers both classical and modern models in deep learning. The chapters of this book span three categories:
The basics of neural networks: Many traditional machine learning models can be understood as special cases of neural networks. An emphasis is placed in the first two chapters on understanding the relationship between traditional mac...
The subject of this book is automated learning, or, as we will more often call it, Machine Learning (ML). That is, we wish to program computers so that they can "learn" from input available to them. Roughly speaking, learning is the process of converting experience into expertise or knowledge. The input to a learning algorithm is training...
At least 80% of all information being collected by enterprises includes geolocation data. The Bing Maps V8 library is a very large collection of JavaScript code that allows web developers to place a map on a webpage, query for data, and manipulate objects on a map, creating a geo-application. In Bing Maps V8 Succinctly, James McCaffrey takes reader...
A broad introduction to algorithms for decision making under uncertainty, introducing the underlying mathematical problem formulations and the algorithms for solving them.
Automated decision-making systems or decision-support systems - used in applications that range from aircraft collision avoidance to breast cancer screening - must be designed...
This book presents an innovative study of the rise of unmarried cohabitation in the Americas, from Canada to Argentina. Using an extensive sample of individual census data for nearly all countries on the continent, it offers a cross-national, comparative view of this recent demographic trend and its impact on the family. The book offers a tour of t...
Computer Vision Metrics provides an extensive survey and analysis of over 100 current and historical feature description and machine vision methods, with a detailed taxonomy for local, regional and global features. This book provides necessary background to develop intuition about why interest point detectors and feature descriptors actually work, ...
This book presents the first comprehensive overview of general methods in Automated Machine Learning (AutoML), collects descriptions of existing systems based on these methods, and discusses the first series of international challenges of AutoML systems. The recent success of commercial ML applications and the rapid growth of the field has created ...
This free book collects the major discussions in divorce research in Europe. It starts with an understanding of divorce trends. Why was divorce increasing so rapidly throughout the US and Europe and do we see signs of a turn? Do cohabitation breakups influence divorce trends or is there a renewed stability on the partner market?In terms of divorce...
This open access book presents the key aspects of statistics in Wasserstein spaces, i.e. statistics in the space of probability measures when endowed with the geometry of optimal transportation. Further to reviewing state-of-the-art aspects, it also provides an accessible introduction to the fundamentals of this current topic, as well as an overvie...
This book provides a comprehensive toolbox of analysis techniques forionospheric multi-satellite missions. The immediate need for this volume was motivatedby the ongoing ESA Swarm satellite mission, but the tools that are described are generaland can be used for any future ionospheric multi-satellite mission with comparableinstrumentation.
In addi...
This book is aimed at computer science undergraduates late in sophomore or early in junior year, supplying a comprehensive background in qualitative and quantitative data analysis, probability, random variables, and statistical methods, including machine learning.With careful treatment of topics that fill the curricular needs for the course, Probab...
The CSS Notes for Professionals book is compiled from Stack Overflow Documentation, the content is written by the beautiful people at Stack Overflow....
The HTML5 Canvas Notes for Professionals book is compiled from Stack Overflow Documentation, the content is written by the beautiful people at Stack Overflow....
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. Although most concepts are relatively simple, there are many of them, and they interact with each other in...
TensorFlow is a free and open-source software library for machine learning. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks.
This book is a somewhat intermediate-level introduction to Tensorflow 2. We will eventually cover everything tf.keras, but no so fast until we implemented t...
The Canvas element is part of HTML5 and allows for dynamic, scriptable rendering of 2D shapes and bitmap images. Through WebGL it allows 3D shapes and images to be displayed. HTML5 Canvas also helps in making 2D games.
It is an unofficial and free HTML5 Canvas book created for educational purposes. All the content is extracted from Stack Overflo...
This open book focuses on processing, modeling, and visualization of anisotropy information, which are often addressed by employing sophisticated mathematical constructs such as tensors and other higher-order descriptors. It also discusses adaptations of such constructs to problems encountered in seemingly dissimilar areas of medical imaging, physi...
This open volume provides readers with an open access protocol collection and wide-ranging recommendations for preclinical renal MRI used in translational research. The chapters in this book are interdisciplinary in nature and bridge the gaps between physics, physiology, and medicine. They are designed to enhance training in renal MRI sciences and ...
This open book focuses on robot introspection, which has a direct impact on physical human - robot interaction and long-term autonomy, and which can benefit from autonomous anomaly monitoring and diagnosis, as well as anomaly recovery strategies. In robotics, the ability to reason, solve their own anomalies and proactively enrich owned knowledge is...
This open book presents a collection of the most up-to-date research results in the field of steel development with a focus on pioneering alloy concepts that result in previously unattainable materials properties. Specifically, it gives a detailed overview of the marriage of high-performance steels of the highest strength and form-ability with dama...
This course is organized around algorithmic issues that arise in machine learning. Modern machine learning systems are often built on top of algorithms that do not have provable guarantees, and it is the subject of debate when and why they work. In this class, we focus on designing algorithms whose performance we can rigorously analyze for fundamen...