en-es
en
0.25
0.5
0.75
1.25
1.5
1.75
2
Kernel Based Identification of Systems with Multiple Outputs Using Nuclear Norm Regularization
Published on Aug 26, 20133192 Views
This contribution introduces a novel identifi cation scheme for nonlinear systems with multiple outputs based on nuclear norm regularization. A kernel based formulation is derived in a primal-dual set
Related categories
Chapter list
Kernel based identification of systems with multiple outputs using nuclear norm regularization00:00
Outline00:17
Overview01:14
Traditional versus proposed approach - 102:27
Traditional versus proposed approach - 202:54
Traditional versus proposed approach - 303:11
Example for multiple output system - 103:23
Example for multiple output system - 204:05
Key contributions and challenges04:31
Nuclear or trace norm05:49
Model formulation in a primal-dual setting - 107:08
Model formulation in a primal-dual setting - 208:42
Advantage of primal-dual approach09:06
Derivation of kernel based model - 111:07
Derivation of kernel based model - 212:33
Formulation of model in terms of dual solution13:41
Model representation15:16
Example: Description16:13
Example: Cross validation18:06
Example: Results18:46
Comparison of optimization problems19:09
Dimensionalities of optimization problems19:45
Solution strategies20:46
Conclusions22:11
Challenges and Outlook23:00