Curve Fitting and Regression with L1 and L2 norms
COURSE PAGE: faculty.washington.edu/kutz/KutzBook/KutzBook.html This lecture introduces the classic curve fitting problem, but with consideration of L2 and L1 norm penalization. The L1 norm is shown to handle outliers quite well and robustify the fitting.
▶︎
Compressive Sensing
▶︎
Nonlinear Regression and Gradient Descent
▶︎
Lecture: Least-Squares Fitting Methods
▶︎
ROC and AUC, Clearly Explained!
▶︎
Applied Linear Algebra: Solvability & Regularization
▶︎
Robust Regression with the L1 Norm
▶︎
Machine Learning Tutorial Python - 17: L1 and L2 Regularization | Lasso, Ridge Regression
▶︎
9. Four Ways to Solve Least Squares Problems
▶︎
Sparsity and the L1 Norm
▶︎
Regression and Ax = b: Over- and under-determined systems
▶︎
Lecture: Principal Componenet Analysis (PCA)
▶︎
Robust, Interpretable Statistical Models: Sparse Regression with the LASSO
▶︎
Gradient Descent, Step-by-Step
▶︎
Applied Linear Algebra GMRES
▶︎
Classic Curve Fitting
▶︎
The Pendulum and Floquet Theory
▶︎
Independent Component Analysis 1
▶︎
Dynamic Mode Decomposition Code
▶︎
Modal Analysis and Mode Coupling
▶︎