en
0.25
0.5
0.75
1.25
1.5
1.75
2
Datum-Wise Classification: A Sequential Approach to Sparsity
Published on Nov 30, 20112817 Views
We propose a novel classification technique whose aim is to select an appropriate representation for each datapoint, in contrast to the usual approach of selecting a representation encompassing the wh
Related categories
Chapter list
Datum-Wise Classi cation: A Sequential Approach to Sparsity00:00
Outline00:17
Motivation - 100:54
Motivation - 201:34
Motivation - 302:10
Motivation - 403:17
Motivation - 503:34
Main Approaches to Sparsity - 104:41
Main Approaches to Sparsity - 205:25
Main Approaches to Sparsity - 305:26
Main Approaches to Sparsity - 405:32
Main Approaches to Sparsity - 505:43
Global Methods05:53
Loss Function - 107:02
Loss Function - 207:48
Loss Function - 308:27
Loss Function - 408:49
Sequential Decision Process09:19
Illustration - 109:57
Illustration - 210:25
Policy11:27
Rollout12:15
Sparsity vs. Accuracy13:48
Feature Use w/ Breast Cancer Dataset15:21
Conclusion16:21
Questions17:55