ML project

Nitride XPS data--SVM

SVM: supervised machine learning classify problem

1. Define problem: a classify problem and we have already know what our correct output should look like, having the idea that there is a relationship between the input and the output. We are trying to predict results in a discrete output. In other words, we are trying to map input variables into discrete categories.
2. Input variables: XPS measured nitride atomic amount level
3. Output: material electrical property: conductive or not
4. Problem: predict conductive property from XPS measured input variables
5. Because it is a classified problem and we have already know what our correct output from some samples, so we can apply support vector machine.
6. Write down cost function with prediction of parameter
7. Use gradient decent to get the parameters

PCA