Todd Moon

Publisher's Note: Products purchased from Third Party sellers are not guaranteed by the publisher for quality, authenticity, or access to any online entitlements included with the product.A comprehensive introduction to the mathematical principles and algorithms in statistical signal processing and modern neural networks. This text is an expanded version of a graduate course on advanced signal processing at the Johns Hopkins University Whiting school program for professionals with students from electrical engineering, physics, computer and data science, and mathematics backgrounds. It covers the theory underlying applications in statistical signal processing including spectral estimation, linear prediction, adaptive filters, and optimal processing of uniform spatial arrays. Unique among books on the subject, it also includes a comprehensive introduction to modern neural networks with examples in time series prediction and image classification. Coverage includes:Mathematical structures of signal spaces and matrix factorizationslinear time-invariant systems and transformsLeast squares filtersRandom variables, estimation theory, and random processesSpectral estimation and autoregressive signal modelslinear prediction and adaptive filtersOptimal processing of linear arraysNeural networks

For Senior/Graduate Level Signal Processing courses. The book is also suitable for a course in advanced signal processing, or for self-study. Mathematical Methods and Algorithms for Signal Processing tackles the challenge of providing students and practitioners with the broad tools of mathematics employed in modern signal processing. Building from an assumed background in signals and stochastic processes, the book provides a solid foundation in analysis, linear algebra, optimization, and statistical signal processing.