Fundamentals: Performance objectives, optimal filtering and estimation, the Wiener solution, orthogonality principle. Adaptation algorithms: MSE performance surface, gradient search methods, the Widrow-Hoff LMS algorithm, convergence speed and misadjustment. Advanced techniques: recursive least-squares algorithms, gradient and least-squares multiple filter, frequency domain algorithms, adaptive pole-zero filters. Applications: system identification, channel equalization, echo cancellation, linear prediction, noise cancellation, speech.
This course may not be repeated for credit.
Prerequisite(s)
- Admission to the PhD in Electrical and Computer Engineering or the MSc in Electrical Engineering.
Sections
This course will be offered next in
Fall 2024.