QuadraticFunction¶
-
class
safe_learning.
QuadraticFunction
(matrix, name='quadratic')¶ A quadratic function.
values(x) = x.T P x
Parameters: - matrix : np.array
2d cost matrix for lyapunov function.
Attributes: parameters
Return the variables within the current scope.
- scope_name
Methods
__call__
(self, \*args, \*\*kwargs)Evaluate the function using the template to ensure variable sharing. build_evaluation
(self, points)Like evaluate, but returns a tensorflow tensor instead. copy_parameters
(self, other_instance)Copy over the parameters of another instance. gradient
(self, points)Return the gradient of the function. -
build_evaluation
(self, points)¶ Like evaluate, but returns a tensorflow tensor instead.
-
copy_parameters
(self, other_instance)¶ Copy over the parameters of another instance.
-
gradient
(self, points)¶ Return the gradient of the function.
-
parameters
¶ Return the variables within the current scope.