ca.nengo.model.plasticity.impl
Class AbstractRealLearningFunction
java.lang.Object
ca.nengo.math.impl.AbstractFunction
ca.nengo.model.plasticity.impl.AbstractRealLearningFunction
- All Implemented Interfaces:
- Function, java.io.Serializable, java.lang.Cloneable
- Direct Known Subclasses:
- ErrorLearningFunction
public abstract class AbstractRealLearningFunction
- extends AbstractFunction
Defines the input available to a real-valued learning rule function.
- Author:
- Trevor Bekolay
- See Also:
- Serialized Form
Method Summary |
AbstractRealLearningFunction |
clone()
|
protected abstract 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). |
float |
getLearningRate()
|
float |
map(float[] from)
Calls deltaOmega. |
void |
setLearningRate(float rate)
|
Methods inherited from class java.lang.Object |
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
myLearningRate
protected float myLearningRate
AbstractRealLearningFunction
public AbstractRealLearningFunction()
- Ensures that the function is of the correct dimension.
map
public float map(float[] from)
- Calls deltaOmega.
- Specified by:
map
in interface Function
- Specified by:
map
in class AbstractFunction
- Parameters:
from
- Must have same length as getDimension()
- Returns:
- result of function operation on arg
- See Also:
Function.map(float[])
deltaOmega
protected abstract 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).
- 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
clone
public AbstractRealLearningFunction clone()
throws java.lang.CloneNotSupportedException
- Specified by:
clone
in interface Function
- Overrides:
clone
in class AbstractFunction
- Throws:
java.lang.CloneNotSupportedException
- See Also:
Object.clone()
setLearningRate
public void setLearningRate(float rate)
- Parameters:
rate
- New learning rate
getLearningRate
public float getLearningRate()