Adaptive Filtering

EECE-595, Section II, Adaptive Filtering

Term: Spring 2003

Instructor: Balu Santhanam

Pre-requisites: EECE-539, EECE-541, knowledge of MATLAB

---

Announcements :

Please check here often because announcements about the course will be posted here.

Course Materials:

Flier for the course
Course Outline/Syllabus

Review material:

Class Notes :

Preliminaries :

Lecture I notes
Lecture II notes
Hilbert Space View of Random Signals
On Signals with Rational Power Spectra
Power Spectrum Factorization
On Autoregressive Processes
On Linear Prediction and Autoregressive Processes

LMS Algorithm and Variants:

Steepest Descent: AR(2) Example
Steepest Descent Versus Newton's Algorithm
Lecture Notes on the LMS Algorithm
Lecture Notes on the NLMS Algorithm
NLMS: Minimum Norm/SVD solution
AR(2) Example: (a) Average Tap-weights and (b) Learning Curve
Lecture Notes on Affine Projection Algorithm
Lecture Notes on Variants of the LMS

RLS Algorithm and Variants:

On Least Squares Inversion
On the Least Squares Algorithm
Exponentially Weighted RLS Algorithm
RLS Algorithm: Design Guidelines
AR(2) Example: RLS Tap-weights

Kalman Filter and Variants:

Discrete Kalman Filter
Relation Between the DKF and RLS
DKF AR(2) Prediction Example: State estimate Kalman gain vector MMSE learning curve
On Wiener and Kalman Filters
Extended Kalman Filter (EKF)
Iterated Extended Kalman Filter (IEKF)

Order Recursive Adaptive Filters:

Gradient Adaptive Lattice
Least Squares Lattice

Problem Sets :

Problem Set # 1.0
Solutions to Problem Set # 1.0
Problem Set # 2.0
Sample output from Problem Set # 2.0
Solution to Problem Set # 2.0

MATLAB Files:

LMS Algorithm
Normalized LMS Algorithm
Recursive Least Squares (RLS) Algorithm
Script for AR(2) example : I (NLMS)
Script for AR(2) example : II (RLS)
Script for AR(2) example : III (DKF)
Discrete Kalman Filter
EKF for Tracking Example