LearningSignal¶
Contents:¶
Learning_signal_Overview
Overview¶
A LearningSignal is a type of ModulatorySignal that is specialized for use with a
LearningMechanism and one or more LearningProjections, to modify the matrix
parameter of the MappingProjections to which they project. A
LearningSignal receives the value of a learning_signal calculated by the LearningMechanism to
which it belongs, which in general is a matrix of weight changes to be made to the matrix
parameter of the MappingProjection(s) being learned. The LearningSignal assigns its learning_signal
as the value of its LearningProjection(s), which convey it to the
MappingProjections` MATRIX ParameterPort(s), which in turn modify the matrix parameter(s) of
the MappingProjection(s) being learned.
Creating a LearningSignal¶
A LearningSignal is created automatically whenever a MappingProjection is specified for learning and the Projection belongs to the same Composition as the
LearningMechanism. LearningSignals can also be specified in the learning_signals argument of the constructor
for a LearningMechanism. Although a LearningSignal can be created directly using its constructor (or any of the
other ways for creating an OutputPort
), this is neither necessary nor advisable, as a
LearningSignal has dedicated Components and requirements for configuration that must be met for it to function properly.
Specifying LearningSignals¶
When a LearningSignal is specified in the learning_signals argument of the constructor for a LearningMechanism, the ParameterPort(s) of the MappingProjection(s) being learned must be specified. This can take any of the following forms:
an existing LearningSignal, or a reference to the class (in which case a default LearningSignal is created);
a ParameterPort, which must be for the
matrix
parameter of the MappingProjection to be learned;
a Projection, which must be either a LearningProjection, or a MappingProjection to which the LearningSignal should send a LearningProjection. In both cases, it is assumed that the LearningProjection projects to the MATRIX ParameterPort of a MappingProjection.
a tuple, with the name of the parameter as its 1st item. and the Projection to which it belongs as the 2nd; note that this is a convenience format, which is simpler to use than a specification dictionary (see below), but precludes specification of any parameters for the LearningSignal.
a specification dictionary, that must contain at least the following two entries:
- NAME:str
the string must be the name of the MappingProjection to be learned; the LearningSignal is named by appending “_LearningSignal” to the name of the Projection.
- PROJECTION:MappingProjection
the MappingProjection must be valid projection specification for the one to be learned.
The dictionary can also contain entries for any other LearningSignal attributes to be specified; see below for a description of LearningSignal attributes.
Structure¶
A LearningSignal is owned by an LearningMechanism, and “trains” one or more MappingProjections
by modulating the value of their matrix
parameters. This is governed by three
attributes of the LearningSignal, as described below.
Projections¶
When a LearningSignal is created, it can be assigned one or more LearningProjections,
using either the projections argument of its constructor, or in an entry of a dictionary assigned to the
params argument with the key PROJECTIONS. These will be assigned to its efferents
attribute. See Port Projections for additional details
concerning the specification of Projections when creating a Port.
Note
Although a LearningSignal can be assigned more than one LearningProjection, all of those Projections will convey
the same learning_signal (received from the LearningMechanism to which the LearningSignal
belongs). Thus, for them to be meaningful, they should project to MappingProjections that are responsible for
identical or systematically-related error signals
(e.g., as in convolutional
networks.
Modulation¶
A LearningSignal has a modulation
attribute that determines how the LearningSignal’s
value
(i.e., its learning_signal
) is used by the
ParameterPort(s) to which it projects to modify the matrix
parameter(s) of their
MappingProjection(s) (see ModulatorySignal Modulation for an explanation of how the
modulation
attribute is specified and used to modify the value of a parameter). The
default value is set to the value of the modulation
attribute of the
LearningMechanism to which the LearningSignal belongs; this is the same for all of the LearningSignals belonging to
that LearningMechanism. The default value of modulation
for a LearningMechanism is
ADDITIVE
, which causes the learning_signal
(i.e., its matrix of weight changes)
to be added to the matrix
parameter of the MappingProjection being learned. The
modulation
can be individually specified for a LearningSignal using a
specification dictionary where the LearningSignal itself is specified, as described
above. The modulation
value of a LearningSignal is
used by all of the LearningProjections that project from that LearningSignal.
LearningSignal Function¶
The function
of a LearningSignal converts the learning_signal
it receives from the LearningMechanism to which it belongs to its value
(i.e., the LearningSignal’s learning_signal
). By default
this is an identity function (Linear
with slope=1 and intercept=0), that simply uses the
LearningMechanism’s learning_signal
as its own. However, the LearningSignal’s
function
can be assigned another TransferFunction
, or any other function that takes a
scalar, ndarray or matrix and returns a similar value.
Note
The index
and assign
attributes of a LearningSignal are automatically assigned and should not be modified.
Execution¶
A LearningSignal cannot be executed directly. It is executed whenever the LearningMechanism to which it belongs is
executed. When this occurs, the LearningMechanism provides the LearningSignal with a
learning_signal
, that is used by its function
to
compute its value
(i.e., its own learning_signal
for that
TRIAL
. That value is used by its LearningProjection(s) to modify the matrix
parameter of the MappingProjection(s) to which the LearningSignal
projects.
Note
The changes in a MappingProjection’s matrix parameter in response to the execution of a LearningSignal are not applied until the MappingProjection is next executed; see Lazy Evaluation for an explanation of “lazy” updating).
Class Reference¶
- class psyneulink.core.components.ports.modulatorysignals.learningsignal.LearningSignal(owner=None, reference_value=None, variable=None, size=None, index=0, assign=None, function=None, modulation=None, modulates=None, params=None, name=None, prefs=None, **kwargs)¶
params=None, projections=None, name=None, prefs=None)
A subclass of ModulatorySignal used by a LearningMechanism to modify the
matrix
parameter of one more more MappingProjection(s). See ModulatorySignal for additional arguments and attributes.- Parameters
function (Function or method : default Linear) – specifies the function used by the LearningSignal to generate its
learning_signal
.modulation (str : default ADDITIVE) – specifies the way in which the
value
of the LearningSignal is used to modify the value of thematrix
parameter for the MappingProjection(s) to which the LearningSignal’s LearningProjection(s) project.modulates (list of Projection specifications) – specifies the LearningProjection(s) to be assigned to the LearningSignal, and that will be listed in its
efferents
attribute (see Projections for additional details).
- function¶
converts
variable
into the LearningSignal’slearning_signal
. The default is theIdentity
Function, that assigns the LearningSignal’svariable
as itslearning_signal
.- Type
TransferFunction : default Linear(slope=1, intercept=0)
- value¶
result of the LearningSignal’s
function
; same as itslearning_signal
.- Type
number, list or np.ndarray
- learning_signal¶
result of the LearningSignal’s
function
; same as itsvalue
.- Type
number, ndarray or matrix
- efferents¶
a list of the LearningProjections assigned to (i.e., that project from) the LearningSignal.
- Type
[List[LearningProjection]]
- modulation¶
determines the way in which the
value
of the LearningSignal is used to modify the value of thematrix
parameter for the MappingProjection to which the LearningSignal’s LearningProjection(s) project.- Type
str
- projection_type¶
alias of
psyneulink.core.components.projections.modulatory.learningprojection.LearningProjection
- exception psyneulink.core.components.ports.modulatorysignals.learningsignal.LearningSignalError(message, component=None)¶