Theano expressions¶
-
blocks.theano_expressions.
hessian_times_vector
(gradient, parameter, vector, r_op=False)[source]¶ Return an expression for the Hessian times a vector.
Parameters: - gradient (
TensorVariable
) – The gradient of a cost with respect to parameter - parameter (
TensorVariable
) – The parameter with respect to which to take the gradient - vector (
TensorVariable
) – The vector with which to multiply the Hessian - r_op (bool, optional) – Whether to use
Rop()
or not. Defaults toFalse
. Which solution is fastest normally needs to be determined by profiling.
- gradient (
-
blocks.theano_expressions.
l2_norm
(tensors, squared=False)[source]¶ Computes the total L2 norm of a set of tensors.
Converts all operands to
TensorVariable
(seeas_tensor_variable()
).Parameters: - tensors (iterable of
TensorVariable
(or compatible)) – The tensors. - squared (bool, optional) – If True, return the squared L2 norm. Default: False.
- tensors (iterable of