|
__init__(self,
input_dim=None,
output_dim=None,
dtype=None)
If the input dimension and the output dimension are
unspecified, they will be set when the 'train' or 'execute'
method is called for the first time. |
|
|
|
_execute(self,
x,
range=None)
Compute the output of the slowest functions. |
|
|
|
|
|
|
|
|
|
|
|
execute(self,
x,
*args,
**kargs)
Compute the output of the slowest functions. |
|
|
|
get_quadratic_form(self,
nr)
Return the matrix H, the vector f and the constant c of the
quadratic form 1/2 x'Hx + f'x + c that defines the output
of the component 'nr' of the SFA node. |
|
|
|
is_invertible(self)
Return True if the node can be inverted, False otherwise. |
|
|
Inherited from object :
__delattr__ ,
__getattribute__ ,
__hash__ ,
__new__ ,
__reduce__ ,
__reduce_ex__ ,
__setattr__
|
|
|
|
|
|
get_eta_values(self,
t=1)
Return the eta values of the slow components learned during
the training phase. |
|
|
|
time_derivative(self,
x)
Compute the linear approximation of the time derivative. |
|
|
|
|
|
__call__(self,
x,
*args,
**kargs)
Calling an instance of Node is equivalent to call
its 'execute' method. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
_refcast(self,
x)
Helper function to cast arrays to the internal dtype. |
|
|
|
|
|
|
|
copy(self,
protocol=-1)
Return a deep copy of the node. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
inverse(self,
y,
*args,
**kargs)
Invert 'y'. |
|
|
|
is_trainable(self)
Return True if the node can be trained, False otherwise. |
|
|
|
is_training(self)
Return True if the node is in the training phase,
False otherwise. |
|
|
|
save(self,
filename,
protocol=-1)
Save a pickled serialization of the node to 'filename'. |
|
|
|
set_dtype(self,
t)
Set internal structures' dtype. |
|
|
|
|
|
|
|
|
|
train(self,
x,
*args,
**kwargs)
Update the internal structures according to the input data 'x'. |
|
|