In this post I’d like to introduce a new feature for the blog … Projects.
Projects are my way of describing a specific data science and/or Machine Learning problem that I’ve solved. Each project is described at more of an overview level without including a lot of the specific statistical, model or coding details. That’s the biggest difference between Projects and the blog Posts.
In these overviews, I focus more on the:
- motivation behind the project
- the approach taken
- the final results
- the conclusions and takeaway lessons
They’re more like reports you might give to someone who is interested in the problem (and solution!) but not the gory details of how the models were trained or the hyperparameters were optimized, for example. I also don’t focus much on how the data were collected.
Some of these Projects come from or are inspired by the course I teach, Machine Learning for Chemistry. Others originate from my research with atmospheric aerosol particles. Still others are just about a topic that I’m interested in.
To begin, I’ve included three Projects that I’ve worked on:
I will, of course, add more Projects later. (I’ve got a neat one with baseball statistics I’m getting ready to post … I mean project … a little multivariate data representation humor for you!)
I include the code (usually MATLAB scripts) I used at the very end of each Project as an appendix in case you are interested in the gory details!