Classical ML

What are the algorithms that fall under Classical/tradition ML

I was able to find below image but not sure if it covers all the Algorithms
[Classic Machine Learning Methods - Machine Learning for Brain Disorders - NCBI Bookshelf]

@thenicknoob I would say that covers a pretty good set of the traditional methods to start with. But I mean in the end there are really quite a few, and among them I see models dealing with time-series analysis (ARIMA, etc), Hidden Markov Models, Random Walks, Monte Carlo Methods, etc, notably missing.

Might I inquire why you are seeking an exhaustive list ? It might be better to focus on the problem you are trying to solve, as even in Deep Learning, ‘one size does not fit all’.


Thanks @Nevermnd for your generous reply. Just wanted a to get a reality check from the community and to check whether I am on the same page as I’m self learning and don’t really have a roadmap or mentor. Trying my best to figure out the classical techniques before I jump into Deep Learning.
The resources which I am referring to at the moment is Andrew NG only. I completed the ML Specialization but couldn’t topics like SVM, Naive bayes, Knn. So a bit confused on why was that left out in the first place.

Any other notable resources you would like to mention like books or anything?

A quick background about me: I have a CS degree

SVM has fallen out of use. It’s too mathematically complicated to train vs. other techniques.

I believe Naive Bayes is covered in the Math for Machine Learning course. It’s more of a statistics method.

KNN is closely related to the K-Means method discussed in the unsupervised portion of MLS.