# ANNs, SVMs, LWR and other Non-linear Methods for Calibration and Classification

## Course Description

While linear methods, such as PLS regression, work in a very wide range of problems of chemical interest, there are times when the relationships between variables are complex and require non-linear modeling methods. Many non-linear methods have been developed, however, we will focus on a few that we have found quite useful. The course begins with a discussion of linearizing transforms. Augmenting with non-linear transforms, e.g. polynomials, is discussed next. Locally Weighted Regression (**LWR**), Artificial Neural Networks (**ANNs**) and Support Vector Machines (**SVMs**) are then considered, with SVMS for both regression and classification considered. The course includes hands-on computer time for participants to work
example problems using PLS_Toolbox and MATLAB.

## Prerequisites

Linear Algebra for Chemometricians, MATLAB for Chemometricians, and Chemometrics I--PCA and Chemometrics II--PLS and Regression or equivalent experience.

## Course Outline

- Introduction

- Why non-linear methods?

- How linear methods deal with non-linear data - Variable Transformations

- Log, sqrt, etc.

- Augmenting with non-linear transforms - Factor based transforms

- PCA Scores and Augmenting

- Polynomial PLS - Locally Weighted Regression

- Weighted Regression

- Distance Measures

- Basing Models on PCA Scores - Support Vector Machines

- SVM basics, shattering theorm

- Kernel functions

- Classification Models

- Regression Models - Artificial Neural Networks

- ANN structures

- Training procedures

- Avoiding overfitting