Yes , high variance of model causes over-fitting. Because you are trying fit each training examples. This will lead a very high order polynomial and a high order polynomial function will cause a weird curve or classifier which tries to fit all the training examples and hence the model will cause high variance.
variance is the difference in fits between the data sets and in overfitting the test errror is more than training error resulting in differences and Hence, results in high variance, while with low bias.
I've watched so many videos on UA-cam!! YOU EXPLAINED IT IN THE BEST WAY!! THANK YOU.
Your videos are superb mam. you have explained so well! thankyou so much! 😊
Very informative. Nice way of teaching
Happy teachers day mam.ur teaching is so good.tq
13:19 can we use entropy as a parameter for pruning the tree?
very nice way of teaching ma`am.
Thanks mam. Very informative video.
What is the error metric?
awesome
Is there any way to download slides of this lecture series?
only way is to enroll in their course in nptel swayam which is a 1000 per course
Can we confirm whether overfitting is same as high variance?
Yes , high variance of model causes over-fitting. Because you are trying fit each training examples. This will lead a very high order polynomial and a high order polynomial function will cause a weird curve or classifier which tries to fit all the training examples and hence the model will cause high variance.
yes
variance is the difference in fits between the data sets and in overfitting the test errror is more than training error resulting in differences and Hence, results in high variance, while with low bias.
Check out code with harry playlist for ml and u rock