Mathematical concepts and computational problems are motivated by applications in computer science. The reader learns by "doing," writing programs to implement the mathematical concepts and using them to carry out tasks and explore the applications. Examples include: error-correcting codes, transformations in graphics, face detection, encryption and secret-sharing, integer factoring, removing perspective from an image, PageRank (Google's ranking algorithm), and cancer detection from cell features. A companion web site, codingthematrix.com provides data and support code. Most of the assignments can be auto-graded online. Over two hundred illustrations, including a selection of relevant "xkcd" comics. Chapters: "The Function," "The Field," "The Vector," "The Vector Space," "The Matrix," "The Basis," "Dimension," "Gaussian Elimination," "The Inner Product," "Special Bases," "The Singular Value Decomposition," "The Eigenvector," "The Linear Program"

    Each major topic is organized into two chapters, beginning with basic concepts that provide necessary background for understanding each data mining technique, followed by more advanced concepts and algorithms.

    When we use consumer products from Google, Microsoft, Facebook, Apple, or Baidu, we are often interacting with a deep learning system. In this volume in the MIT Press Essential Knowledge series, computer scientist John Kelleher offers an accessible and concise but comprehensive introduction to the fundamental technology at the heart of the artificial intelligence revolution.Kelleher explains that deep learning enables data-driven decisions by identifying and extracting patterns from large datasets; its ability to learn from complex data makes deep learning ideally suited to take advantage of the rapid growth in big data and computational power. Kelleher also explains some of the basic concepts in deep learning, presents a history of advances in the field, and discusses the current state of the art. He describes the most important deep learning architectures, including autoencoders, recurrent neural networks, and long short-term networks, as well as such recent developments as Generative Adversarial Networks and capsule networks. He also provides a comprehensive (and comprehensible) introduction to the two fundamental algorithms in deep learning: gradient descent and backpropagation. Finally, Kelleher considers the future of deep learning—major trends, possible developments, and significant challenges.

    This comprehensive work covers both statistical and symbolic approaches to language processing; it shows how they can be applied to important tasks such as speech recognition, spelling and grammar correction, information extraction, search engines, machine translation, and the creation of spoken-language dialog agents. The following distinguishing features make the text both an introduction to the field and an advanced reference guide.- UNIFIED AND COMPREHENSIVE COVERAGE OF THE FIELDCovers the fundamental algorithms of each field, whether proposed for spoken or written language, whether logical or statistical in origin.- EMPHASIS ON WEB AND OTHER PRACTICAL APPLICATIONSGives readers an understanding of how language-related algorithms can be applied to important real-world problems.- EMPHASIS ON SCIENTIFIC EVALUATIONOffers a description of how systems are evaluated with each problem domain.- EMPERICIST/STATISTICAL/MACHINE LEARNING APPROACHES TO LANGUAGE PROCESSINGCovers all the new statistical approaches, while still completely covering the earlier more structured and rule-based methods.

    The technology is powerful but it is still a tool—one used by people to apply human ingenuity, imagination, and problem-solving skills to see trends, patterns, anomalies, and relationships in what were once inscrutable or unmanageable issues. In their years spent working with hundreds of companies, governments, and non-profit organizations, Josh Sullivan and Angela Zutavern have consulted with a wide range of leaders developing new capabilities that lead to new business models, the creation of breakthrough products and services, and potential solutions to vexing global problems. Their stories include Ford developing not just smarter cars but also smarter roads and cities; an oceanographer obtaining a holistic map of the oceans, with ramifications for both the fishing industry but for humanity at large; and health care entrepreneurs developing new products that significantly reduce heart attack fatalities.These are but a few examples of leaders tapping the power of the digital world and creatively collaborating with computers. New capabilities are developed that then give birth to new business models as leaders envision and shape the future. Businesses are reaching goals that until recently seemed difficult, if not impossible, to attain. The winnings will go to organizations that take steps to deliver "impossible strategies," and The Mathematical Corporation provides leaders with the new way to think and work in this era of data science and drive the revolution.

    But as this hands-on guide demonstrates, programmers comfortable with Python can achieve impressive results in deep learning with little math background, small amounts of data, and minimal code. How? With fastai, the first library to provide a consistent interface to the most frequently used deep learning applications.Authors Jeremy Howard and Sylvain Gugger show you how to train a model on a wide range of tasks using fastai and PyTorch. You'll also dive progressively further into deep learning theory to gain a complete understanding of the algorithms behind the scenes.Train models in computer vision, natural language processing, tabular data, and collaborative filteringLearn the latest deep learning techniques that matter most in practiceImprove accuracy, speed, and reliability by understanding how deep learning models workDiscover how to turn your models into web applicationsImplement deep learning algorithms from scratchConsider the ethical implications of your work

    In The Master Algorithm, Pedro Domingos lifts the veil to give us a peek inside the learning machines that power Google, Amazon, and your smartphone. He assembles a blueprint for the future universal learner--the Master Algorithm--and discusses what it will mean for business, science, and society. If data-ism is today's philosophy, this book is its bible.

    It shows readers how to step back from coding to consider design strategies and attempt to get into the head of the designer.

    You can think of Python as your tool to solve problems that are far beyond the capability of a spreadsheet. It is an easy-to-use and easy-to learn programming language that is freely available on Windows, Macintosh, and Linux computers. There are free downloadable copies of this book in various electronic formats and a self-paced free online course where you can explore the course materials. All the supporting materials for the book are available under open and remixable licenses. This book is designed to teach people to program even if they have no prior experience.

    This book teaches basic Artificial Intelligence algorithms such as dimensionality, distance metrics, clustering, error calculation, hill climbing, Nelder Mead, and linear regression. These are not just foundational algorithms for the rest of the series, but are very useful in their own right. The book explains all algorithms using actual numeric calculations that you can perform yourself. Artificial Intelligence for Humans is a book series meant to teach AI to those without an extensive mathematical background. The reader needs only a knowledge of basic college algebra or computer programming—anything more complicated than that is thoroughly explained. Every chapter also includes a programming example. Examples are currently provided in Java, C#, R, Python and C. Other languages planned.

    JavaScript lets designers add sparkle and life to web pages, while more complex JavaScript has led to the rise of Ajax -- the latest rage in web development that allows developers to create powerful and more responsive applications in the browser window."Learning JavaScript" introduces this powerful scripting language to web designers and developers in easy-to-understand terms. Using the latest examples from modern browser development practices, this book teaches you how to integrate the language with the browser environment, and how to practice proper coding techniques for standards-compliant web sites. By the end of the book, you'll be able to use all of the JavaScript language and many of the object models provided by web browsers, and you'll even be able to create a basic Ajax application.

    Professors Gary Marcus and Ernest Davis have spent their careers at the forefront of AI research and have witnessed some of the greatest milestones in the field, but they argue that a computer winning in games like Jeopardy and go does not signal that we are on the doorstep of fully autonomous cars or superintelligent machines. The achievements in the field thus far have occurred in closed systems with fixed sets of rules. These approaches are too narrow to achieve genuine intelligence. The world we live in is wildly complex and open-ended. How can we bridge this gap? What will the consequences be when we do? Marcus and Davis show us what we need to first accomplish before we get there and argue that if we are wise along the way, we won't need to worry about a future of machine overlords. If we heed their advice, humanity can create an AI that we can trust in our homes, our cars, and our doctor's offices. Reboot provides a lucid, clear-eyed assessment of the current science and offers an inspiring vision of what we can achieve and how AI can make our lives better.

    Written by the world’s foremost PowerPivot blogger and practitioner, the book’s concepts and approach are introduced in a simple, step-by-step manner tailored to the learning style of Excel users everywhere. The techniques presented allow users to produce, in hours or even minutes, results that formerly would have taken entire teams weeks or months to produce. It includes lessons on the difference between calculated columns and measures; how formulas can be reused across reports of completely different shapes; how to merge disjointed sets of data into unified reports; how to make certain columns in a pivot behave as if the pivot were filtered while other columns do not; and how to create time-intelligent calculations in pivot tables such as “Year over Year” and “Moving Averages” whether they use a standard, fiscal, or a complete custom calendar. The “pattern-like” techniques and best practices contained in this book have been developed and refined over two years of onsite training with Excel users around the world, and the key lessons from those seminars costing thousands of dollars per day are now available to within the pages of this easy-to-follow guide. This updated second edition covers new features introduced with Office 2015.

    We are living in an age where data comes in abundance, and thanks to the self-learning algorithms from the field of machine learning, we can turn this data into knowledge. Automated speech recognition on our smart phones, web search engines, e-mail spam filters, the recommendation systems of our favorite movie streaming services – machine learning makes it all possible.Thanks to the many powerful open-source libraries that have been developed in recent years, machine learning is now right at our fingertips. Python provides the perfect environment to build machine learning systems productively.This book will teach you the fundamentals of machine learning and how to utilize these in real-world applications using Python. Step-by-step, you will expand your skill set with the best practices for transforming raw data into useful information, developing learning algorithms efficiently, and evaluating results.You will discover the different problem categories that machine learning can solve and explore how to classify objects, predict continuous outcomes with regression analysis, and find hidden structures in data via clustering. You will build your own machine learning system for sentiment analysis and finally, learn how to embed your model into a web app to share with the world

    With it has come vast amounts of data in a variety of fields such as medicine, biology, finance, and marketing. The challenge of understanding these data has led to the development of new tools in the field of statistics, and spawned new areas such as data mining, machine learning, and bioinformatics. Many of these tools have common underpinnings but are often expressed with different terminology. This book describes the important ideas in these areas in a common conceptual framework. While the approach is statistical, the emphasis is on concepts rather than mathematics. Many examples are given, with a liberal use of color graphics. It should be a valuable resource for statisticians and anyone interested in data mining in science or industry. The book's coverage is broad, from supervised learning (prediction) to unsupervised learning. The many topics include neural networks, support vector machines, classification trees and boosting—the first comprehensive treatment of this topic in any book. Trevor Hastie, Robert Tibshirani, and Jerome Friedman are professors of statistics at Stanford University. They are prominent researchers in this area: Hastie and Tibshirani developed generalized additive models and wrote a popular book of that title. Hastie wrote much of the statistical modeling software in S-PLUS and invented principal curves and surfaces. Tibshirani proposed the Lasso and is co-author of the very successful An Introduction to the Bootstrap. Friedman is the co-inventor of many data-mining tools including CART, MARS, and projection pursuit.