SpikingNeuralNet (boone)

java.lang.Object
- boone.NeuralNet
- - boone.spike.SpikingNeuralNet

All Implemented Interfaces:

Storable, java.lang.Cloneable
```
public class SpikingNeuralNet
extends NeuralNet
```
The class SpikingNeuralNet represents a spiking neural network. A SpikingNeuralNet supports neuron models that explicitly model the neurons potential and spike generation. Use base classes SpikingNeuron and SpikingLink to construct a spiking neural network.

A SpikingNeuralNetwork has following responsibilities:
- Store the neurons and links
- Store the network input
- Initialize the processing of the network input
- Store and manage the spikes generated by the neurons
- Schedule the spikes and propagate spikes between neurons
To use a SpikingNeuralNetwork perform following steps:
- Construct the network like any standard NeuralNet
- Provide the firing times for the input neurons:
  - Create a new SpikeSet
  - Set the firing times for the input neurons with SpikeSet.setInputSpikes(Neuron, List)
  - Call setInput(SpikeSet)
- Innervate the network with innervate()
The network offers two different modes that define the scheduling strategy for the spikes. The network output is independent of the selected mode. The current mode is indicated by the return value of getRealTimeMode().

In default mode, once the network is innervated, all calculations are performed as soon as the necessary information is available. There is no relation between the real time and the firing time of the spike, indicated by its timestamp. However, if a call to setRealTimeMode() sets the network to real-time mode before it is innervated, a spike with firing time t is approximately propagated t milliseconds after the network was innervated.
Version:

$Id: SpikingNeuralNet.java 2285 2015-08-04 jmory $

Author:

Johannes Mory

Field Summary
- Fields inherited from class boone.NeuralNet
  FEEDFORWARD, filter, inputNeurons, layers, links, maxCycles, neurons, outputNeurons, props, RECURRENT, topology, trainer, UNKNOWN, zeroInputAfterFirstCycle

Constructor Summary

Constructors
Constructor and Description

SpikingNeuralNet()
Create a new, empty SpikingNeuralNet.

Constructors
Constructor and Description
`SpikingNeuralNet()` Create a new, empty `SpikingNeuralNet`.

Method Summary

All Methods Static Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`void`	`addLink(Link link)` Adds a link.
`void`	`addNeuron(Neuron neuron)` Add a neuron to our list.
`void`	`fromXML(org.jdom2.Element element)` Loads the network attributes from XML.
`double`	`getLatestSpikeTime()` Returns the latest spike time of the spikes currently in the buffer.
`boolean`	`hasMoreSpikes()` Checks if currently there are unprocessed spikes.
`void`	`innervate()` Innervates the network by calling `innervate(double)` with infinite execution time.
`void`	`innervate(double timeLimit)` Innervate the network, i.e.
`boolean`	`isActive()` Checks if the scheduler thread is active.
`boolean`	`isRealTimeMode()` Return whether real-time mode is activated.
`static SpikingNeuralNet`	`load(java.io.File file, IOFilter filter)` Loads a SpikingNeuralNet from the given file using the set file filter.
`boolean`	`removeLink(Link link)` remove a link from our network.
`boolean`	`removeNeuron(Neuron neuron)` Removes a neuron and updates the associated links, but no link lists.
`void`	`replaceLink(Link oldLink, Link newLink)` replace a link with another.
`void`	`replaceNeuron(Neuron oldNeuron, Neuron newNeuron)` Replace a neuron with another.
`void`	`resume()` Resume scheduling and propagating spikes.
`void`	`setInput(SpikeSet inputs)` Set the firing times for the input neurons as defined in the specified `SpikeSet`.
`void`	`setRealTimeMode(boolean realTime)` Set whether the network should run in real-time mode.
`void`	`stop()` Stop scheduling and propagating spikes.

Methods inherited from class boone.NeuralNet
addLayer, clone, getFilter, getHiddenNeuronCount, getInputNeuron, getInputNeuronCount, getLink, getLinkCount, getLinkID, getMaxCycles, getNeuron, getNeuronCount, getNeuronID, getNeuronIndex, getOutput, getOutputNeuron, getOutputNeuronCount, getOutputNeuronIndex, getTopology, getTrainer, getZeroInputAfterFirstCycle, linkNet, randomize, save, setFilter, setInput, setInput, setMaxCycles, setTopology, setTrainer, setZeroInputAfterFirstCycle, toString, toXML

Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

- Constructor Detail
  - SpikingNeuralNet
```
public SpikingNeuralNet()
```
    Create a new, empty SpikingNeuralNet.
- Method Detail
  - innervate
```
public void innervate()
```
    Innervates the network by calling innervate(double) with infinite execution time.
    
    Overrides:
    
    innervate in class NeuralNet
  - innervate
```
public void innervate(double timeLimit)
```
    Innervate the network, i.e. let the input neurons start generating spikes. First resets the network to its initial state by removing all (potential) spikes from the local caches. However, there may be spikes in the global buffer, e.g., the given input. Next a new thread that schedules and propagates the generated spikes is created. The network stops scheduling spikes as soon as it encounters a spike with a firing time less than the specified value. Use isActive() to check the state of the network. There could be a lock, if the network does not generate any more spikes, before reaching the time limit. Please, use hasMoreSpikes() ()} to check this situation.
    
    Parameters:
    
    timeLimit - the upper limit for the firing times [ms] of the generated spikes
  - stop
```
public void stop()
```
    Stop scheduling and propagating spikes.
  - resume
```
public void resume()
```
    Resume scheduling and propagating spikes.
  - isActive
```
public boolean isActive()
```
    Checks if the scheduler thread is active. If it is not active, the thread has ended. However, there may be still unprocessed spikes. You may further process them using resume().
  - hasMoreSpikes
```
public boolean hasMoreSpikes()
```
    Checks if currently there are unprocessed spikes.
    
    Returns:
    
    true, if more spikes to be processed.
  - getLatestSpikeTime
```
public double getLatestSpikeTime()
```
    Returns the latest spike time of the spikes currently in the buffer.
    
    Returns:
    
    the time stamp, 0, if no spikes in buffer
  - setInput
```
public void setInput(SpikeSet inputs)
```
    Set the firing times for the input neurons as defined in the specified SpikeSet. If a specific input neuron should not generate any spikes, SpikeSet.getInputSpikes(Neuron) should return null or an empty list for the specific input neuron. Note that the global buffer is cleared before adding the spikes, so as to avoid confusion with potential old spikes.
    
    Parameters:
    
    inputs - the firing times for the input neurons
  - isRealTimeMode
```
public boolean isRealTimeMode()
```
    Return whether real-time mode is activated.
    
    Returns:
    
    true if real-time mode is activated
  - setRealTimeMode
```
public void setRealTimeMode(boolean realTime)
```
    Set whether the network should run in real-time mode.
  - addNeuron
```
public void addNeuron(Neuron neuron)
```
    Description copied from class: NeuralNet
    
    Add a neuron to our list. Specifically, adds the neuron to the internal neuron list, and to the input and/or output neuron lists if the neuron is an input/output neuron.
    
    Overrides:
    
    addNeuron in class NeuralNet
    
    Parameters:
    
    neuron - the neuron to add
  - replaceNeuron
```
public void replaceNeuron(Neuron oldNeuron,
                          Neuron newNeuron)
```
    Description copied from class: NeuralNet
    
    Replace a neuron with another. The neuron is also disconnected and re-connected in all links. All links of the old neuron are added to the new neuron. If the old neuron is the same as the new neuron (w.r.t. ==), does nothing.
    
    Overrides:
    
    replaceNeuron in class NeuralNet
  - removeNeuron
```
public boolean removeNeuron(Neuron neuron)
```
    Description copied from class: NeuralNet
    
    Removes a neuron and updates the associated links, but no link lists.
    
    Overrides:
    
    removeNeuron in class NeuralNet
    
    Returns:
    
    true, if neuron removed
  - addLink
```
public void addLink(Link link)
```
    Description copied from class: NeuralNet
    
    Adds a link.
    
    Overrides:
    
    addLink in class NeuralNet
    
    Parameters:
    
    link - a link
  - replaceLink
```
public void replaceLink(Link oldLink,
                        Link newLink)
```
    Description copied from class: NeuralNet
    
    replace a link with another. The neuron is also disconnected and re-connected in all links. Finally, the old neuron's outputLinks and inputLinks lists are cleared.
    
    NOTE: The solution may look a bit complicated, but this is prepared for Special, extended links.
    
    Overrides:
    
    replaceLink in class NeuralNet
  - removeLink
```
public boolean removeLink(Link link)
```
    Description copied from class: NeuralNet
    
    remove a link from our network.
    NOTE: The Link is always disconnected before removing from the neurons using Link.disconnect() .
    
    Also please note that there is no removeLink(int index) method, because the link needs to be looked up anyway, to disconnect it.
    
    Overrides:
    
    removeLink in class NeuralNet
    
    Returns:
    
    whether the link was found in our list of links.
    
    See Also:
    
    Link.disconnect()
  - load
```
public static SpikingNeuralNet load(java.io.File file,
                                    IOFilter filter)
                             throws java.io.IOException
```
    Loads a SpikingNeuralNet from the given file using the set file filter. If loading is successful, the given filter is attached to the net. Do not forget to configure the filter for the correct state of compression of the file to be loaded.
    
    Parameters:
    
    file - file to load the network from
    
    Returns:
    
    this neural network, null if problems
    
    Throws:
    
    java.io.IOException
  - fromXML
```
public void fromXML(org.jdom2.Element element)
```
    Loads the network attributes from XML.
    
    Specified by:
    
    fromXML in interface Storable
    
    Overrides:
    
    fromXML in class NeuralNet
    
    Parameters:
    
    element - the main net element

Class SpikingNeuralNet

Field Summary

Fields inherited from class boone.NeuralNet

Constructor Summary

Method Summary

Methods inherited from class boone.NeuralNet

Methods inherited from class java.lang.Object

Constructor Detail

SpikingNeuralNet

Method Detail

innervate

innervate

stop

resume

isActive

hasMoreSpikes

getLatestSpikeTime

setInput

isRealTimeMode

setRealTimeMode

addNeuron

replaceNeuron

removeNeuron

addLink

replaceLink

removeLink

load

fromXML