Combining Data Sources Nonlinearly for Cell Nucleus Classification of Renal Cell Carcinoma thumbnail
slide-image
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Combining Data Sources Nonlinearly for Cell Nucleus Classification of Renal Cell Carcinoma

Published on Oct 17, 20112882 Views

In kernel-based machine learning algorithms, we can learn a combination of different kernel functions in order to obtain a similarity measure that better matches the underlying problem instead of usin

Related categories

Chapter list

Combining Data Sources Nonlinearly for Cell Nucleus Classification of Renal Cell Carcinoma00:00
Outline00:08
Introduction00:24
Our Contribution01:05
Methodology - 101:38
Methodology - 202:45
Constructing Kernels03:46
Linear MKL Algorithms - 104:13
Linear MKL Algorithms - 204:40
Our Nonlinear Variant - 105:35
Our Nonlinear Variant - 206:59
Our Nonlinear Variant - 307:19
Data Set - 108:42
Data Set - 209:16
Experiments - 109:29
Experiments - 209:52
SVM Results10:46
MKL Results11:28
Training Times13:11
Conclusion13:51
Some Notes14:20