An AutoAssociativeLearningMechanism is a subclass of LearningMechanism, modified for use with a
RecurrentTransferMechanism to train its
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 LearningMechanism 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
matrixparameter of an ‘AutoAssociativeProjection` (typically, the
recurrent_projectionof a RecurrentTransferMechanism), but not an ERROR_SIGNAL OutputPort.
it has no
error_sourceattributes; instead, it has a single
activity_sourceattribute that identifies the source of the activity vector used by the Mechanism’s
functiontakes as its
variablea list or 1d np.array of numeric entries, corresponding in length to the AutoAssociativeLearningMechanism’s ACTIVATION_INPUT InputPort; and it returns a
learning_signal(a weight change matrix assigned to the Mechanism’s LEARNING_SIGNAL OutputPort), but not necessarily an
learning_ratecan 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 LearningMechanism, a scalar can also be specified to scale the entire weight change matrix (see
learning_ratefor additional details).
An AutoAssociativeLearningMechanism executes in the same manner as standard LearningMechanism, with two exceptions: * 1) its execution can be enabled or disabled by setting the `learning_enabled
<RecurrentTransferMechanism.learning_enabled>` attribute of the RecurrentTransferMechanism with which it is associated (identified in its
2) it is executed during the
execution phaseof the System’s execution. Note that this is different from the behavior of supervised learning algorithms (such as
BackPropagation), that are executed during the
learning phaseof a System’s execution
- class psyneulink.library.components.mechanisms.modulatory.learning.autoassociativelearningmechanism.AutoAssociativeLearningMechanism(variable, function=Hebbian, learning_rate=None, learning_signals=LEARNING_SIGNAL, modulation=ADDITIVE, params=None, name=None, prefs=None)¶
Implements a LearningMechanism that modifies the
matrixparameter of an AutoAssociativeProjection (typically the
recurrent_projectionof 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) with the
valueof the Mechanism’s InputPort (see
variablefor additional details).
learning_signals (List[parameter of Projection, ParameterPort, Projection, tuple[str, Projection] or dict] : default None) – specifies the
matrixto be learned (see
learning_signalsfor details of specification).
function (LearningFunction or function : default Hebbian) – specifies the function used to calculate the AutoAssociativeLearningMechanism’s
learning_signalattribute. 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 matrix”).
learning_rate (float : default None) – specifies the learning rate for the AutoAssociativeLearningMechanism. (see
has a single item, that serves as the template for the input required by the AutoAssociativeLearningMechanism’s
function, corresponding to the
the OutputPort that is the
senderof the AutoAssociativeProjection that the Mechanism trains.
has a single item, that contains the AutoAssociativeLearningMechanism’s single ACTIVATION_INPUT InputPort.
the Projection with the
matrixparameter being trained by the AutoAssociativeLearningMechanism. It is always the first Projection listed in the AutoAssociativeLearningMechanism’s
all of the AutoAssociativeProjections modified by the AutoAssociativeLearningMechanism; the first item in the list is always the
the function used to calculate the
learning_signal(assigned to the AutoAssociativeLearningMechanism’s LearningSignal(s)). It’s
variablemust 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
functionto 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 to the
valueof 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
Systemto which the AutoAssociativeLearningMechanism belongs. If it is
None, then the
learning_ratespecified for the Process to which the AutoAssociativeLearningMechanism belongs belongs is used; and, if that is
None, then the
learning_ratefor the System to which it belongs is used. If all are
None, then the
functionis 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
matrixparameter for the AutoAssociativeLearningMechanism’s`learned_projections <AutoAssociativeLearningMechanism.learned_projections>`; 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 the
matrixparameter of the AutoAssociativeProjection(s) trained by the AutoAssociativeLearningMechanism. Although in most instances an AutoAssociativeLearningMechanism is used to train a single AutoAssociativeProjection, like a standard LearningMechanism, 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_signalattribute, 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 (user-specified) OutputPorts.
the first item is the
valueof the LearningMechanism’s
learning_signal, followed by the
values of any additional (user-specified) OutputPorts.
- _parse_function_variable(variable, context=None)¶
Parses the variable passed in to a Component into a function_variable that can be used with the Function associated with this Component
- _validate_variable(variable, context=None)¶
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_output_ports(runtime_params=None, context=None)¶
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
- exception psyneulink.library.components.mechanisms.modulatory.learning.autoassociativelearningmechanism.AutoAssociativeLearningMechanismError(error_value)¶