11d Machine Learning: Bayesian Linear Regression
HTML-код
- Опубликовано: 15 июл 2024
- Lecture on Bayesian linear regression. By adopting the Bayesian approach (instead of the frequentist approach of ordinary least squares linear regression) we can account for prior information and directly model the distributions of the model parameters by updating with training data.
Follow along with the demonstration workflow:
github.com/GeostatsGuy/Python...
THIS IS THE ONLY GOOD EXPLANATION OF THIS!!! thank you
Your explanation was explicit , thank you.
Great explanation. Thank you
Great explanation and channel!
Thank you very much.
Thank you so much!!!!
very clear ....Thank you
It was a great explanation, thank you very much!
I was wondering if you could tell the world a little bit about Bayesian Model Selection. One more time, thanks a lot.
Cool video
YOU ARE GREAT
Thank you Jakob. I hope the content is helpful!
How is the distributions of uncertainty in Bayesian linear regression, differ from the confidence intervals of parameters in a frequentist linear regression ?
hello thank you for this video. I just have a question regarding the equation at 10:46 for the first term of the top part of the fraction shouldn't it be P(y|X,beta) instead of P(y,X|beta)?
14:05 - isn't it intractable because the model parameters beta (not the features X) are continuous?
Also, in 2:31, shouldn't the equation at the bottom have (b0 + b1*x) rather than having a minus sign ?
Howdy shan19key. Good catch. I'll fix the lecture and this will be updated in the next iteration. Appreciation!
Hi there thanks for your lectures I've benefited heaps from them.
I wanted to ask what book you refer to in this video "hasty book on statistical learning" ?
Kind regards
Hastie, Tibshirani, Friedman - Elements of Statistical Learning
Nice video ... Can you use Bayesian regression to model nonlinear data?
Greetings from Colombia. Thanks
Yes, you can! After all, the "linear" term in linear regression refers to the linearity in the parameter, not the data.
13:07 Posterior term is wrong in the text. What is written in the text is likelihood. But otherwise thanks.
Great catch, Amin. I'll add errata to comments, correct this and post in the update. I appreciate the assistance!
good content, too bad you've been using your considerable intellect to benefit big oil. Yuck. What a waste.