#include <kernelwrapper.h>
Inheritance diagram for InputVectorWrapper


Public Methods | |
| InputVectorWrapper (string name_i, int e) | |
| virtual void | activate (bool = false, bool = true) |
| Activate the map given the current inputs. More... | |
| virtual Activity | activity (Subscript i, Subscript j) const |
| Overrides activity(), et cetera so that plotting can be re-written to use this interface; then the original structure can be eliminated entirely. More... | |
| virtual const ActivityMatrix& | const_activity () const |
| Returns a const matrix of the current activity values. More... | |
| virtual void | add_input (const string& name, const ActivityMatrix& input_region, WeightFunction& fn, Length size_scale=1.0) |
| Add a new input region; accepts a unary function of size_scale to initialize the weights. More... | |
| virtual Dimensions | input_dimensions (WeightFunction& fn, Length size_scale=1.0) |
| Computes input dimensions that would be required to avoid border effects. More... | |
| virtual const WeightMatrix | get_weights (const string& name="", int i=0, int j=0) const |
| Returns weights from the given unit from the group of weights with the given name. More... | |
Definition at line 14 of file kernelwrapper.h.
|
|
|
|
|
Activate the map given the current inputs. Must be implemented by derived classes. Reimplemented from NeuralRegion. |
|
|
Overrides activity(), et cetera so that plotting can be re-written to use this interface; then the original structure can be eliminated entirely.
Reimplemented from NeuralRegion. Definition at line 22 of file kernelwrapper.h. |
|
|
Add a new input region; accepts a unary function of size_scale to initialize the weights.
Reimplemented from InternalNeuralRegion. |
|
|
Returns a const matrix of the current activity values.
Reimplemented from NeuralRegion. Definition at line 23 of file kernelwrapper.h. |
|
|
Returns weights from the given unit from the group of weights with the given name. The weights returned may e.g. be a constant set of weights for all units regardless, or they may be generated on the fly, so bear that in mind. If a region does not have any weights with the specified name, it should return an empty (0x0) matrix. Reimplemented from InternalNeuralRegion. |
|
|
Computes input dimensions that would be required to avoid border effects.
Reimplemented from InternalNeuralRegion. |
1.2.1 written by Dimitri van Heesch,
© 1997-2000