OpenANN
1.1.0
An open source library for artificial neural networks.
|
A helper class for specifying weight constrains in a higher-order neural network Derive a new class from this interface and simple reimplement the function call operator for the corresponding higher-order term. More...
#include <SigmaPi.h>
Public Member Functions | |
Constraint () | |
virtual | ~Constraint () |
virtual double | operator() (int p1, int p2) const |
function call operator for corresponding second-order nodes More... | |
virtual double | operator() (int p1, int p2, int p3) const |
function call operator for corresponding third-order nodes More... | |
virtual double | operator() (int p1, int p2, int p3, int p4) const |
function call operator for corresponding fourth-order nodes More... | |
virtual bool | isDefault () const |
A helper class for specifying weight constrains in a higher-order neural network Derive a new class from this interface and simple reimplement the function call operator for the corresponding higher-order term.
e.g. constraint(p1, p2, p3) for third-order nodes.
NEVER overwrite the isDefault method. (This is only important for unconstrained higher-order nodes)
|
inline |
|
inlinevirtual |
|
virtual |
|
virtual |
function call operator for corresponding second-order nodes
Reimplemented in OpenANN::SlopeConstraint, and OpenANN::DistanceConstraint.
|
virtual |
function call operator for corresponding third-order nodes
Reimplemented in OpenANN::TriangleConstraint.
|
virtual |
function call operator for corresponding fourth-order nodes