en
0.25
0.5
0.75
1.25
1.5
1.75
2
Clustering and Projected Clustering with Adaptive Neighbors
Published on Oct 07, 20142488 Views
Many clustering methods partition the data groups based on the input data similarity matrix. Thus, the clustering results highly depend on the data similarity learning. Because the similarity measurem
Related categories
Chapter list
Clustering and Projected Clustering with Adaptive Neighbors00:00
Outline00:10
Deterministic Neighbors and Probabilistic Neighbors00:29
Rules for Computing the Probabilistic Neighbors01:22
Computing the Probabilistic Neighbors02:16
Probabilistic Neighbors Assignment for All the Data03:12
Clustering with Adaptive Neighbors (CAN)03:46
The CAN Clustering Algorithm04:39
Connection to K-means Clustering04:53
Discussions on CAN Clustering Algorithm05:25
Projected Clustering with Adaptive Neighbors (PCAN)06:13
The PCAN Clustering Algorithm07:09
Connection to Linear Discriminant Analysis (LDA)07:36
Discussions on PCAN Clustering Algorithm08:11
K-Means Result on 196 Clusters08:31
CAN Result on 196 Clusters08:42
Numerical Results on 196 Clusters09:03
Projection Results of PCAN on Synthetic Data - 109:22
Projection Results of PCAN on Synthetic Data - 210:58
Clustering Results on Real Benchmark Datasets11:49
Results of PCAN on Real Benchmark Datasets - 112:14
Results of PCAN on Real Benchmark Datasets - 212:24
Results of PCAN on Real Benchmark Datasets - 312:53
Conclusions13:13
Acknowledgement14:08