File:SlowFeatureAnalysis-OptimizationProblem.png
From Scholarpedia
Size of this preview: 800 × 377 pixels.
Original file (1,029 × 485 pixels, file size: 16 KB, MIME type: image/png)
The optimization problem solved by slow feature analysis is to find functions \(\mathbf{g}(\mathbf{x})\) that extract from a quickly varying input signal \(\mathbf{x}(t)\) slowly varying features \(\mathbf{y}(t)=\mathbf{g}(\mathbf{x}(t))\). It is crucial that this is done instantaneously, i.e. one time slice of the output is base on just one (or very few time slice of the input), as indicated by the yellow background.
File history
Click on a date/time to view the file as it appeared at that time.
| Date/Time | Thumbnail | Dimensions | User | Comment | |
|---|---|---|---|---|---|
| current | 09:45, 4 March 2009 | | 1,029 × 485 (16 KB) | Laurenz Wiskott (Talk | contribs) | The optimization problem solved by slow feature analysis is to find functions <math>{\bf g}({\bf x})</math> that extract from a quickly varying input signal <math>{\bf x}(t)</math> slowly varying features <math>{\bf y}(t)={\bf g}({\bf x}(t))</math>. It i |
- Edit this file using an external application (See the setup instructions for more information)
File usage
The following page links to this file:
