What can we learn from an overview of current-ish Practical or Applied Machine Learning Course Syllabi

[MarkBruns]

We would expect that we will want to consider several different basic approaches, random forests, decision trees, neural nets ... and then refine our approach as we consider things like data availability and how this material fits with we might already know about the problem like basic fluid dynamics of clogs, enzymatic action in digesting sludge or biomass or strategies to stop root growth into sewer lines.

Along the way, we might learn things we don't really want to be reminded of, ie that it's very similar to spam or financial fraud detection, so we could treat it as an email cleaner or bank fraud anomaly detection problem, but not many have data acquisition devices on the sewer line, ie maybe that can change, but the need for specific kinds of IoT plumbing monitors would be informed by what we could do with it if we only had it.

https://www.coursera.org/learn/practical-machine-learning#syllabus

https://c.d2l.ai/stanford-cs329p/syllabus.html#data-i

https://www.tutorialspoint.com/practical-machine-learning-using-python/index.asp

https://www.udemy.com/course/machine-learning-practical/

https://www.tutorialspoint.com/practical-machine-learning-using-python/index.asp