Easy introduction to gaussian process regression (uncertainty models)

Gaussian process regression (GPR) is a probabilistic approach to making predictions. GPRs are easy to implement, flexible, and fully probabilistic models. Overall, they provide a powerful tool in many application areas.
In this video, we give an animated introduction to GPRs, focusing on the idea and main components.From this point, hopefully, you will be able to quickly dive into the theory and build your own GPR.'
GPR book:
www.gaussianprocess.org/gpml/c...
GP video:
• ML Tutorial: Gaussian ...
Adapting probability distribution:
www.math.chalmers.se/~rootzen/...
0:00 Intro Predictions
1:09 Idea of Gaussian process regression
1:33 Gaussian processes
2:32 Adapting the probability distribution
3:20 Putting it together
LinkedIn: / nicolai-palm-97160b219
-------------------------------------------------------------------------------
Data Science to go: paretos.com

[@ovaisjafri422]

Thanks for summarizing it all in such a short introduction. Grateful!

[@fjturner123]

Thank you! This is a really clear and understandable introduction to GP regression.

[@frankl1]

The best intro to GP ever

[@samiramir5606]

I agree

[@knvcsg1839]

Concise and Crisp Explanation! Really liked it

[@TechTribeCommunity]

Very good introduction - thanks!

[@user-vi3lz3uh2i]

非常感谢，讲解知识简单易懂，大师

[@peterrichards5107]

Thanks for posting this great introduction.

[@nhchau]

Thank you very much for your clear and concise explanation.

[@suchasunshine]

incredible explanation, thank you

[@dilipkumar2k6]

Very nicely explained, thank you 🎉

[@user-en3zj8jt2s]

Thank you for the perfect explanation. Can we call the last part as bayesian optimization, i.e. the combination of gaussian process and conditional probability mechanism?

[@ilyeshamdi50]

Great explanation bro !

[@shubhamjuneja6313]

So good!

[@seansullivan6986]

Thanks. Very helpful.

[@ButilkaRomm]

So we build iteratively a distribution over all the functions that pass through yi. The distribution is based on Gaussian Processes and we have a formula to build it iteratively. Gaussian Processes are defined by a mean() and covariance() functions, so it is possible to calculate the "mean" of our distribution (over functions that go through yi) which is the most likely function that passes through yi.

[@nicolaipalm7563]

There are some mathematical issues when you want to define GPR properly (f.e. Why are Gaussian processes determined by their mean and cov functions or what we mean when talking about “measurement over functions”) but you got the idea!

[@TM-do8ip]

Thank you , this is great bro

[@Navaneet76]

nice explanation👍

[@user-wr4yl7tx3w]

this is really good intro. is there a continuation of this?

[@nicolaipalm7563]

There will be … soon 🤓

[@dapadmavathi684]

excellent, Thank you.

[@amothe83]

Awesome 💯

[@OrdenJust]

Good video.

[@OliverJanShD]

How do you come up with these animations? They are very good!

[@nicolaipalm7563]

This is the manim Python library - you can create amazing animations with this! 🤩

[@jonathandawson3091]

Absolutely no reason why we must trust the observed points 100%, right? But the regressor seems to pass through them with 0 variance which seems very wrong.

[@PS-eu6qk]

Video style looks copy of 3blue1brown channel🤣🤣