Machine Learning Interview Question - Closed Form Solution for Linear Regression!

In this video Prateek Bhayia, discusses how to derive the optimal Theta for linear regression problem and its effectiveness when compared to gradient descent method. The squared error loss function derivative is set 0 to find the right theta for the algorithm. Check out the next video for the implementation.
Checkout complete course on - online.codingbl...

[@Biggzlar]

Excellent video - very well explained without cutting corners or omitting important mathematical concepts.

[@ataykaragulov]

Great ,everything is in detailed explanation huge thanks !!!

[@CodingBlocksIndia]

Glad it was helpful!

[@AmitKhuranaSir]

Thanx a lot bro you explained in very simple language My professor is not like YOU...

[@pyro226]

Needs to be louder

[@TheGaneshshow]

You are awesome!!, Thank you very much!

[@elhonchobc]

the mean squared error function should not have 1/2 at the beginning unless our sample size is 2. it should be 1/m instead

[@aayushbisht9666]

sir whats difference btw L=(ypred - y)^2 and L=(y-ypred)^2 in multipe linear regression its L=(y-ypred)^ so result was (yT -(XB)T)(y-XB) but in Ridge Regression its L=(y-ypred)^2 which results (XB-y)T (XB -y)

[@omarallam4548]

Great 🙏

[@niharikamiryalavk]

very good explanation . thank you

[@CodingBlocksIndia]

Glad it was helpful!

[@mohammadsubhani836]

Bro volume is too low. You can improve on that parameter.

[@yurahulivatyi7955]

thank you! It was very helpful!

[@Vikram-wx4hg]

Super!

[@arindamchak]

Volume is too low to grasp anything

[@somayehseifi8269]

i want this in python , and i could not find it . can you plz give me the link

[@liferajib]

Can you explain what closed form solution means ?

[@shiweixiao2574]

get answer directly from x， y ？

[@coolk5802]

Cool :)