en
0.25
0.5
0.75
1.25
1.5
1.75
2
Batch Discovery of Recurring Rare Classes toward Identifying Anomalous Samples
Published on Oct 07, 20142117 Views
We present a clustering algorithm for discovering rare yet significant recurring classes across a batch of samples in the presence of random effects. We model each sample data by an infinite mixture o
Related categories
Chapter list
Batch Discovery of Recurring Rare Classes toward Identifying Anomalous Samples00:00
Problem and Challenges - 100:14
Problem and Challenges - 201:04
Motivation01:51
Related Work03:23
ASPIRE - 104:58
ASPIRE - 205:19
Generative Model05:52
Independent Modeling by DPM - 106:13
Independent Modeling by DPM - 206:53
Introducing dependencies by HDPM07:10
Modeling Random Effects by HDPM-RE - 107:52
Modeling Random Effects by HDPM-RE - 208:33
Proposed Generative Model (ASPIRE) - 108:56
Proposed Generative Model (ASPIRE) - 209:36
Model Inference10:08
Illustration - 111:00
Illustration - 211:23
Illustration - 311:49
Illustration - 412:03
Application: Discovering Rare Cell Populations - 112:39
Application: Discovering Rare Cell Populations - 212:52
Application: Discovering Rare Cell Populations - 313:49
Application: Discovering Rare Cell Populations - 413:53
Conclusions14:25