Bagging and Boosting 

You are absolutely the best teacher I have run into since my foray intyto data science. Bravo!

Correction! @8:30: The probability of an instance getting excluded or being not selected in the nth draw is: (1-1/n)^n. So, it needs a little bit of correction.

Thank you, dear Sudesha. It is very good to see women teaching ML topics, most of the videos are from men.

Wrong at 6:20, Replacement means that for every bag, samples are drawn from the complete datatset regardless of what went inside previous bag. It does not mean that inside each bag you will have repeated observations.

Is there any playlist for these lectures or we have to do boosting in random forest ?

Mam u r god i passed this subject caz of u only....guruji u r great

Liked the wy the weights in Boosting were explained

7:59 how come the probability will be as mentioned if we are considering both sample size and dataset size as n, then all the instances are chosen, so probability will be 1. right??

Thank you Madam for such a lecture on this topic. Prof Sripati, AoT

Maam where are you now, 2022 needs you

good explanation madam

At 2:43, the learner will underfit, not overfit with the small dataset?

Awesome.

Why the lectures are all over the place, there is no sequence. If a title for the video is given, it would be easy to search and view what is required to view.

Ma'am please consider the feedback in the comments section, you are hampering the image of IIT

mam,iam invented bagging machine i have some doubts

At 8:30 the probability will be 1 - that quantity

Thank you very much mam

Please mam provide notes for every topic

The formula is wrong it should be 1 - (1- 1/n) ^ n

Horrible english. Could not understand some words.