Engelska

<p>Linear algebra and the foundations of deep learning, together at last! From Professor Gilbert Strang, acclaimed author of Introduction to Linear Algebra, comes Linear Algebra and Learning from Data, the first textbook that teaches linear algebra together with deep learning and neural nets. </p><p>This readable yet rigorous textbook contains a complete course in the linear algebra and related mathematics that students need to know to get to grips with learning from data. Included are: the four fundamental subspaces, singular value decompositions, special matrices, large matrix computation techniques, compressed sensing, probability and statistics, optimization, the architecture of neural nets, stochastic gradient descent and backpropagation.</p>

This extensively classroom-tested text takes an innovative approach to explaining software testing that defines it as the process of applying a few precise, general-purpose criteria to a structure or model of the software. The book incorporates cutting-edge developments, including techniques to test modern types of software such as OO, web applications, and embedded software. This revised second edition significantly expands coverage of the basics, thoroughly discussing test automaton frameworks, and it adds new, improved examples and numerous exercises. The theory of coverage criteria is carefully and cleanly explained to help students understand concepts before delving into practical applications, while extensive use of the JUnit test framework gives students practical experience in a test framework popular in the industry. Exercises, meanwhile, feature specifically tailored tools that allow students to check their own work. The book's website also offers an instructor's manual, PowerPoint slides, testing tools for students, and example software programs in Java.