2min chapter

Surviving ChatGPT with Christian Hubicki

Machine Learning Archives - Software Engineering Daily

CHAPTER

Is There a One Size Fits All Problem for Machine Learning?

There isn't a one size fits all problem for learning in the context of robotics or anything else and I think that that's what that's why there's this beautiful zoo of different machine learning algorithms. So when you're incredibly limited you have to deal with some really low order methods like it can be that simple but then there's sort of a sliding scale that you can use depending on how much data you have. There are things called like a Gaussian process regressions GPRs and GPs and those are nice for a certain scale of data now those don't scale up to the kinds of scale stuff you get for a neural net. You have to go up to a neural net when

00:00