2
$\begingroup$

I'm looking for a summary of the pros and cons of different machine learning models in practise.

Something that includes: - How the model works - What kinds of outliers will be misrepresented by the model - Effect of different parameters in each model on speed/performance

$\endgroup$
1
  • $\begingroup$ I doubt that this exists, I guess everything you will find is a summary like this. If you look at how Wikipedia outlines Machine Learning, I have the feeling a comprehensive summary would still be overwhelming. I would suggest to look into more specific summaries like Supervised Learning or, like you already mentioned, Deep Learning. $\endgroup$
    – André
    Sep 24, 2018 at 8:28

1 Answer 1

1
$\begingroup$

Can't comment due to low reputation, but as a comprehensive summary I'd recommend Elements of Statistical Learning by Hastie et. al. It reviews most current state-of-the-art ML methods, together with the classics, is free of charge (big thanks to the authors!), and even has a nice accompanying R package.

It's probably not the source you've expected, but is really a nice place to start, especially for practitioners.

$\endgroup$

Not the answer you're looking for? Browse other questions tagged or ask your own question.