ca.nengo.model.plasticity.impl
Class ErrorLearningFunction
java.lang.Object
ca.nengo.math.impl.AbstractFunction
ca.nengo.model.plasticity.impl.AbstractRealLearningFunction
ca.nengo.model.plasticity.impl.ErrorLearningFunction
- All Implemented Interfaces:
- Function, java.io.Serializable, java.lang.Cloneable
public class ErrorLearningFunction
- extends AbstractRealLearningFunction
A learning function that uses information from the ensemble to modulate the rate
of synaptic change.
- Author:
- Trevor Bekolay
- See Also:
- Serialized Form
Constructor Summary |
ErrorLearningFunction(float[] gain,
float[][] encoders)
Requires information from the post population to modulate learning. |
ErrorLearningFunction(float[] gain,
float[][] encoders,
boolean oja)
Requires information from the post population to modulate learning. |
ErrorLearningFunction(NEFEnsembleImpl ens)
Extracts information from the post population to modulate learning. |
Method Summary |
ErrorLearningFunction |
clone()
|
protected float |
deltaOmega(float input,
float time,
float currentWeight,
float modInput,
float originState,
int postIndex,
int preIndex,
int dim)
A learning rule that defines how the connection weight changes on
each timestep (or longer, depending on the plasticity interval). |
Methods inherited from class java.lang.Object |
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
ErrorLearningFunction
public ErrorLearningFunction(float[] gain,
float[][] encoders)
- Requires information from the post population to modulate learning.
- Parameters:
gain
- Gain (scale) of the neurons in the post populationencoders
- Encoders (phi tilde) of the neurons in the post population
ErrorLearningFunction
public ErrorLearningFunction(float[] gain,
float[][] encoders,
boolean oja)
- Requires information from the post population to modulate learning.
- Parameters:
gain
- Gain (scale) of the neurons in the post populationencoders
- Encoders (phi tilde) of the neurons in the post population
ErrorLearningFunction
public ErrorLearningFunction(NEFEnsembleImpl ens)
- Extracts information from the post population to modulate learning.
- Parameters:
ens
- Post population
deltaOmega
protected float deltaOmega(float input,
float time,
float currentWeight,
float modInput,
float originState,
int postIndex,
int preIndex,
int dim)
- Description copied from class:
AbstractRealLearningFunction
- A learning rule that defines how the connection weight changes on
each timestep (or longer, depending on the plasticity interval).
- Specified by:
deltaOmega
in class AbstractRealLearningFunction
- Parameters:
input
- The activity coming into the synapse from its inputstime
- The current simulation timecurrentWeight
- The current connection weight between the pre and post neuronsmodInput
- The modulatory input, for this particular dimension (see dim)originState
- The state of the origin from the postsynaptic population,
for this particular dimension (see dim)postIndex
- The neuron index in the post-synaptic populationpreIndex
- The neuron index in the pre-synaptic populationdim
- The dimension of the modulatory input and the origin state- See Also:
AbstractRealLearningFunction.deltaOmega(float,float,float,float,float,int,int,int)
clone
public ErrorLearningFunction clone()
throws java.lang.CloneNotSupportedException
- Specified by:
clone
in interface Function
- Overrides:
clone
in class AbstractRealLearningFunction
- Throws:
java.lang.CloneNotSupportedException
- See Also:
Object.clone()