Internet Explorer 11 is being discontinued by Microsoft in August 2021.
If you have difficulties viewing the site on Internet Explorer 11 we
recommend using a different browser such as Microsoft Edge, Google
Chrome, Apple Safari or Mozilla Firefox.
Update 13th September 2024: Our systems are now restored following recent technical disruption, and we’re working hard to catch up on publishing. We apologise for the inconvenience caused. Find out more
Providing a logical framework for student learning, this is the first textbook on adversarial learning. It introduces vulnerabilities of deep learning, then demonstrates methods for defending against attacks and making AI generally more robust. To help students connect theory with practice, it explains and evaluates attack-and-defense scenarios alongside real-world examples. Feasible, hands-on student projects, which increase in difficulty throughout the book, give students practical experience and help to improve their Python and PyTorch skills. Book chapters conclude with questions that can be used for classroom discussions. In addition to deep neural networks, students will also learn about logistic regression, naïve Bayes classifiers, and support vector machines. Written for senior undergraduate and first-year graduate courses, the book offers a window into research methods and current challenges. Online resources include lecture slides and image files for instructors, and software for early course projects for students.
Providing a logical framework for student learning, this is the first textbook on adversarial learning. It introduces vulnerabilities of deep learning, then demonstrates methods for defending against attacks and making AI generally more robust. To help students connect theory with practice, it explains and evaluates attack-and-defense scenarios alongside real-world examples. Feasible, hands-on student projects, which increase in difficulty throughout the book, give students practical experience and help to improve their Python and PyTorch skills. Book chapters conclude with questions that can be used for classroom discussions. In addition to deep neural networks, students will also learn about logistic regression, naïve Bayes classifiers, and support vector machines. Written for senior undergraduate and first-year graduate courses, the book offers a window into research methods and current challenges. Online resources include lecture slides and image files for instructors, and software for early course projects for students.
Using easy-to-follow mathematics, this textbook provides comprehensive coverage of block codes and techniques for reliable communications and data storage. It covers major code designs and constructions from geometric, algebraic, and graph-theoretic points of view, decoding algorithms, error control additive white Gaussian noise (AWGN) and erasure, and dataless recovery. It simplifies a highly mathematical subject to a level that can be understood and applied with a minimum background in mathematics, provides step-by-step explanation of all covered topics, both fundamental and advanced, and includes plenty of practical illustrative examples to assist understanding. Numerous homework problems are included to strengthen student comprehension of new and abstract concepts, and a solutions manual is available online for instructors. Modern developments, including polar codes, are also covered. An essential textbook for senior undergraduates and graduates taking introductory coding courses, students taking advanced full-year graduate coding courses, and professionals working on coding for communications and data storage.
Using easy-to-follow mathematics, this textbook provides comprehensive coverage of block codes and techniques for reliable communications and data storage. It covers major code designs and constructions from geometric, algebraic, and graph-theoretic points of view, decoding algorithms, error control additive white Gaussian noise (AWGN) and erasure, and dataless recovery. It simplifies a highly mathematical subject to a level that can be understood and applied with a minimum background in mathematics, provides step-by-step explanation of all covered topics, both fundamental and advanced, and includes plenty of practical illustrative examples to assist understanding. Numerous homework problems are included to strengthen student comprehension of new and abstract concepts, and a solutions manual is available online for instructors. Modern developments, including polar codes, are also covered. An essential textbook for senior undergraduates and graduates taking introductory coding courses, students taking advanced full-year graduate coding courses, and professionals working on coding for communications and data storage.
This textbook offers a fresh approach to digital signal processing (DSP) that combines heuristic reasoning and physical appreciation with sound mathematical methods to illuminate DSP concepts and practices. It uses metaphors, analogies and creative explanations, along with examples and exercises to provide deep and intuitive insights into DSP concepts. Practical DSP requires hybrid systems including both discrete- and continuous-time components. This book follows a holistic approach and presents discrete-time processing as a seamless continuation of continuous-time signals and systems, beginning with a review of continuous-time signals and systems, frequency response, and filtering. The synergistic combination of continuous-time and discrete-time perspectives leads to a deeper appreciation and understanding of DSP concepts and practices. For upper-level undergraduatesIllustrates concepts with 500 high-quality figures, more than 170 fully worked examples, and hundreds of end-of-chapter problems, more than 150 drill exercises, including complete and detailed solutionsSeamlessly integrates MATLAB throughout the text to enhance learning
This textbook offers a fresh approach to digital signal processing (DSP) that combines heuristic reasoning and physical appreciation with sound mathematical methods to illuminate DSP concepts and practices. It uses metaphors, analogies and creative explanations, along with examples and exercises to provide deep and intuitive insights into DSP concepts. Practical DSP requires hybrid systems including both discrete- and continuous-time components. This book follows a holistic approach and presents discrete-time processing as a seamless continuation of continuous-time signals and systems, beginning with a review of continuous-time signals and systems, frequency response, and filtering. The synergistic combination of continuous-time and discrete-time perspectives leads to a deeper appreciation and understanding of DSP concepts and practices. For upper-level undergraduatesIllustrates concepts with 500 high-quality figures, more than 170 fully worked examples, and hundreds of end-of-chapter problems, more than 150 drill exercises, including complete and detailed solutionsSeamlessly integrates MATLAB throughout the text to enhance learning
