What email address or phone number would you like to use to sign in to Docs.com?
If you already have an account that you use with Office or other Microsoft services, enter it here.
Or sign in with:
Signing in allows you to download and like content, and it provides the authors analytical data about your interactions with their content.
Embed code for: Weekly Report Vincent 20160815-20160820
Select a size
Weekly Report Vincent 20160815-20160820
MONDAY, 2016/08/15 Today, it is holiday to celebrate Korean Independence Day. Nevertheless, I go to the lab to prepare the data I am going to use for the classification task. TUESDAY, 2016/08/16 10:30-12:00 | Annisa's seminar• I attend one main activity today: Today I prepare my paper to be submitted to Journal of Multimedia Information System (JMIS, https://jmis.org). WEDNESDAY, 2016/08/17 Label Powerset (LP)○ Binary Relevance (BR)○ Ranking by Pairwise Comparison (RPC)○ Calibrated Label Ranking (CLR)○ Simple Problem Transformation Methods1. Tree-Based Boosting○ Lazy Learning○ Discriminative SVM-Based Methods○ Simple Algorithm Adaptation Methods2. Shared Subspace○ Dimensionality Reduction and Subspace Based Methods3. Ensemble Methods4. Generative Modeling for Multi-label Data5. Today, I read a paper titled "A Literature Survey on Algorithms for Multi-label Learning", written by Mohammad S Sorower. It contains various methods, such as: THURSDAY, 2016/08/18 15:00-16:00 | Bayu's seminar• I attend one main activity today: Learning with Multiple Labels: Disjoint Case1. Multitask Learning2. Multi-Instance Multi-Label Learning (MIML)3. Today I continue reading the paper from yesterday. I learn about the variations of the problem, such as: FRIDAY, 2016/08/19 12:00-14:30 | Friday Prayer in Sasang• I attend one main activity today: Exact Match Ratio (EMR) Accuracy (A) Precision (P) Example-baseda. Partitions1. Today I continue reading the paper from two days ago. I learn about the evaluation metrics, such as: Weekly Report Vincent 2016/08/15-2016/08/20 PKNU Page 1 Precision (P) Recall ® F1-Measure (F) Hamming Loss (HL) -Evaluation Label-basedb. One Error (O)○ Coverage (C)○ Ranking Loss (RL)○ Average Precision (AP)○ Rankings2. Hierarchical3. The result is as follows. PKNU Page 2 PKNU Page 3