Creating an AutoAssociativeLearningMechanism
An AutoAssociativeLearningMechanism can be created directly by calling its constructor, but most commonly it is created
automatically when a RecurrentTransferMechanism is configured for learning,
(identified in its
An AutoAssociativeLearningMechanism is identical to a Learning Mechanism in all respects except the following:
it has only a single ACTIVATION_INPUT InputPort, that receives a MappingProjection from an OutputPort of
the RecurrentTransferMechanism with which it is associated (identified by the
it has a single LEARNING_SIGNAL OutputPort that sends a LearningProjection to the
matrix parameter of an ‘AutoAssociativeProjection` (typically, the
recurrent_projection of a RecurrentTransferMechanism),
but not an ERROR_SIGNAL OutputPort.
it has no
error_source attributes; instead, it has a single
activity_source attribute that identifies the source of the activity vector
used by the Mechanism’s
function takes as its
a list or 1d np.array of numeric entries, corresponding in length to the AutoAssociativeLearningMechanism’s
ACTIVATION_INPUT InputPort; and it returns a
(a weight change matrix assigned to the Mechanism’s LEARNING_SIGNAL OutputPort), but not necessarily an
learning_rate can be specified as a 1d or 2d array (or
matrix) to scale the contribution made, respectively, by individual elements or connections among them,
to the weight change matrix; as with a standard Learning Mechanism, a scalar can also be specified to scale
the entire weight change matrix (see
An AutoAssociativeLearningMechanism executes in the same manner as standard Learning Mechanism, with two exceptions:
* 1) its execution can be enabled or disabled by setting the `learning_enabled
AutoAssociativeLearningMechanism(variable, function=Hebbian, learning_rate=None, learning_signals=LEARNING_SIGNAL, modulation=ADDITIVE, params=None, name=None, prefs=None)
Implements a Learning Mechanism that modifies the
matrix parameter of an
AutoAssociativeProjection (typically the
of a RecurrentTransferMechanism).
variable (List or 2d np.array : default None) – it must have a single item that corresponds to the value required by the AutoAssociativeLearningMechanism’s
function; it must each be compatible (in number and type)
value of the Mechanism’s InputPort (see
variable for additional details).
learning_signals (List[parameter of Projection, ParameterPort, Projection, tuple[str, Projection] or dict] : default None) – specifies the
matrix to be learned (see
learning_signals for details of specification).
function (LearningFunction or function : default Hebbian) – specifies the function used to calculate the AutoAssociativeLearningMechanism’s
learning_signal attribute. It must take as its variable argument a
list or 1d array of numeric values (the “activity vector”) and return a list, 2d np.array or np.matrix
representing a square matrix with dimensions that equal the length of its variable (the “weight change
learning_rate (float : default None) – specifies the learning rate for the AutoAssociativeLearningMechanism. (see
learning_rate for details).
has a single item, that serves as the template for the input required by the AutoAssociativeLearningMechanism’s
function, corresponding to the
value of the
the OutputPort that is the
sender of the AutoAssociativeProjection
that the Mechanism trains.
has a single item, that contains the AutoAssociativeLearningMechanism’s single ACTIVATION_INPUT InputPort.
the Projection with the
matrix parameter being trained by the
AutoAssociativeLearningMechanism. It is always the first Projection listed in the
all of the AutoAssociativeProjections modified by the
AutoAssociativeLearningMechanism; the first item in the list is always the
the function used to calculate the
(assigned to the AutoAssociativeLearningMechanism’s LearningSignal(s)).
variable must be a list or 1d np.array of numeric entries, corresponding in
length to the AutoAssociativeLearningMechanism’s ACTIVATION_INPUT (primary) InputPort.
LearningFunction or function : default Hebbian
determines the learning rate used by the AutoAssociativeLearningMechanism’s
function to scale the weight change matrix it returns. If it is a scalar, it is used to multiply the weight change matrix; if it is a 2d array or matrix,
it is used to Hadamard (elementwise) multiply the weight matrix (allowing the contribution of individual
connections to be scaled); if it is a 1d np.array, it is used to Hadamard (elementwise) multiply the input
function (i.e., the
value of the
AutoAssociativeLearningMechanism’s ACTIVATION_INPUT InputPort,
allowing the contribution of individual units to be scaled). If specified, the value supersedes the
learning_rate assigned to any
System to which the AutoAssociativeLearningMechanism belongs.
If it is
None, then the
learning_rate specified for the Process to which the
AutoAssociativeLearningMechanism belongs belongs is used; and, if that is
None, then the
learning_rate for the System to which it belongs is used. If all are
None, then the
default_learning_rate for the
function is used (see learning_rate
for additional details).
float, 1d or 2d np.array, or np.matrix of numeric values : default None
the value returned by
function, that specifies
the changes to the weights of the
matrix parameter for the
It is assigned as the value of the AutoAssociativeLearningMechanism’s LearningSignal(s) and, in turn, its LearningProjection(s).
2d ndarray or matrix of numeric values
list of all of the LearningSignals for the AutoAssociativeLearningMechanism, each of which
sends one or more LearningProjections to the ParameterPort(s) for
matrix parameter of the AutoAssociativeProjection(s) trained by the AutoAssociativeLearningMechanism. Although in most instances an
AutoAssociativeLearningMechanism is used to train a single AutoAssociativeProjection, like a standard
Learning Mechanism, it can be assigned additional LearningSignals and/or LearningProjections to train
additional ones; in such cases, the value for all of the LearningSignals is the
the same: the AutoAssociativeLearningMechanism’s
learning_signal attribute, based on its
activity_source. Since LearningSignals are OutputPorts, they are also listed in the AutoAssociativeLearningMechanism’s
list of all of the LearningProjections <LearningProjection>` from the AutoAssociativeLearningMechanism, listed
in the order of the LearningSignals to which they belong (that is, in the order they are
listed in the
list of the AutoAssociativeLearningMechanism’s OutputPorts, beginning with its
learning_signals, and followed by any additional
the first item is the
value of the LearningMechanism’s
learning_signal, followed by the
of any additional (user-specified) OutputPorts.
Parses the variable passed in to a Component into a function_variable that can be used with the
Function associated with this Component
Validate that variable has only one item: activation_input.
_execute(variable=None, context=None, runtime_params=None)
Execute AutoAssociativeLearningMechanism. function and return learning_signal
(2D np.array) self.learning_signal
Update the weights for the AutoAssociativeProjection for which this is the AutoAssociativeLearningMechanism
Must do this here, so it occurs after LearningMechanism’s OutputPort has been updated.
This insures that weights are updated within the same trial in which they have been learned