quiz4_2009

Fill in the following blanks for the weights

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: e list in Part A. Remember to only use the classifiers you circled in Part B. Round 1 Round 2 Round 3 w1 w2 w3 w4 w5 w6 w7 w8 w9 w10 h ε α Part D (10 points) What is the final classifier you find when performing three rounds of Boosting: How many of the data points does your final classifier classify correctly? 9 Part E (10 points) Wesley Windham-Pryce, a fellow consultant, has noticed a few correlations between some of the classifiers you used, and so he suggests using a new set of weak classifiers consisting of each pair of your original weak classifiers logically ANDed or ORed together (so for instance, two of the new classifiers would be "Emo=Y OR Evil=Y" and "Sparkly=N AND Transforms=Y"). He believes that you will be able to classify large vampire datasets more quickly and with fewer rounds of boosting using his system. Do you agree or disagree with Wesley? Explain your argument briefly and precisely. 10 Tear off sheet—you need not hand this in. ID Name Vampire Evil Emo Transforms Sparkly # Romantic Interests ID 1 Dracula Y Y N Y N 5 1 2 Angel Y N Y Y N 5 2 3 Edward Cullen Y N Y N Y 1 3 4 Saya Otonashi Y N Y N N 3 4 5 Lestat de Lioncourt Y N Y N N 5 5 6 Bianca St. Claire Y Y N Y N 5 6 7 Mircalla Karnstein Y Y N Y N 5 7 8 Sailor Moon N N N Y Y 1 8 9 Squall Leonhart N N Y N N 1 9 N N N N N 5 10 10 Circe 11 0.2 0.1 M M H F 0.7 T 0.8 V V H Z R M Z F F 0.01 F T 0.4 T F 0.5 T 12 V T 0.6 R F 0.1 T 0.3...
View Full Document

This document was uploaded on 03/17/2014 for the course EECS 6.034 at MIT.

Ask a homework question - tutors are online