Tata Institute of Fundamental Research
AdaBoost - New Boosting Algorithm
Student Seminar
Speaker:
Tapan Shah
Organiser:
Ankush Agarwal
Date:
Friday, 21 Dec 2012, 15:00 to 16:30
Venue:
A-212 (STCS Seminar)
(Scan to add to calendar)
Abstract:
Boosting is a general method to improve the accuracy of any givenlearning algorithm. I will introduce a new method of boosting - AdaBoost- and discuss its advantages compared to other traditional methods of boosting like "boost-by-majority" algorithm. I will also try to give an intuitive explanation as to why boosting does not suffer from overfitting.
Reference:
http://link.springer.com/chapter/10.1007%2F3-540-59119-2_166?LI=true
| Speaker: | Tapan Shah |
| Organiser: | Ankush Agarwal |
| Date: | Friday, 21 Dec 2012, 15:00 to 16:30 |
| Venue: | A-212 (STCS Seminar) |
(Scan to add to calendar)
Abstract:
Boosting is a general method to improve the accuracy of any givenlearning algorithm. I will introduce a new method of boosting - AdaBoost- and discuss its advantages compared to other traditional methods of boosting like "boost-by-majority" algorithm. I will also try to give an intuitive explanation as to why boosting does not suffer from overfitting.
Reference:
http://link.springer.com/chapter/10.1007%2F3-540-59119-2_166?LI=true
Reference:
http://link.springer.com/chapter/10.1007%2F3-540-59119-2_166?LI=true