Class NEATNetwork
- All Implemented Interfaces:
Prototype,Setup,Serializable,Cloneable
- See Also:
-
Field Summary
FieldsModifier and TypeFieldDescriptionThe neat individual we belong toA list of input nodes for this network.A list of all nodes for this network.A list of output nodes for this network.static final Stringstatic final doubleconstant used for the sigmoid function -
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionvoidactivate(EvolutionState state) Activates the net such that all outputs are active.voidAdd a new input node.voidAdd a new output node.voidbuildNetwork(NEATIndividual individual) Create the phenotype (network) from the genotype (genome).clone()Creates a new individual cloned from a prototype, and suitable to begin use in its own evolutionary context.Returns the default base for this prototype.booleanvoidflush()double[]Produces an array of activation results, one per output node.static boolean[]hasPath(EvolutionState state, NEATNode toNode, NEATNode fromNode, int threshold) This checks a POTENTIAL link between start from fromNode to toNode to use count and threshold to jump out in the case of an infinite loop.static voidhasPath(EvolutionState state, NEATNode toNode, NEATNode fromNode, HashSet<NEATNode> set, int level, int threshold, boolean[] results) The helper function to check if there is a path from fromNode to toNode.voidloadSensors(double[] vals) Takes an array of sensor values and loads it into SENSOR inputs ONLY.intmaxDepth()Find the maximum number of neurons between an output and an input.booleanCheck if not all output are active.voidsetup(EvolutionState state, Parameter base) Sets up the object by reading it from the parameters stored in state, built off of the parameter base base.
-
Field Details
-
P_NETWORK
- See Also:
-
SIGMOID_SLOPE
public static final double SIGMOID_SLOPEconstant used for the sigmoid function- See Also:
-
individual
The neat individual we belong to -
nodes
A list of all nodes for this network. -
inputs
A list of input nodes for this network. -
outputs
A list of output nodes for this network.
-
-
Constructor Details
-
NEATNetwork
public NEATNetwork()
-
-
Method Details
-
setup
Description copied from interface:PrototypeSets up the object by reading it from the parameters stored in state, built off of the parameter base base. If an ancestor implements this method, be sure to call super.setup(state,base); before you do anything else.For prototypes, setup(...) is typically called once for the prototype instance; cloned instances do not receive the setup(...) call. setup(...) may be called more than once; the only guarantee is that it will get called at least once on an instance or some "parent" object from which it was ultimately cloned.
-
defaultBase
Description copied from interface:PrototypeReturns the default base for this prototype. This should generally be implemented by building off of the static base() method on the DefaultsForm object for the prototype's package. This should be callable during setup(...).- Specified by:
defaultBasein interfacePrototype
-
clone
Description copied from interface:PrototypeCreates a new individual cloned from a prototype, and suitable to begin use in its own evolutionary context.Typically this should be a full "deep" clone. However, you may share certain elements with other objects rather than clone hem, depending on the situation:
- If you hold objects which are shared with other instances, don't clone them.
- If you hold objects which must be unique, clone them.
- If you hold objects which were given to you as a gesture of kindness, and aren't owned by you, you probably shouldn't clone them.
- DON'T attempt to clone: Singletons, Cliques, or Populations, or Subpopulation.
- Arrays are not cloned automatically; you may need to clone an array if you're not sharing it with other instances. Arrays have the nice feature of being copyable by calling clone() on them.
Implementations.
- If no ancestor of yours implements clone(), and you have no need to do clone deeply, and you are abstract, then you should not declare clone().
- If no ancestor of yours implements clone(),
and you have no need to do clone deeply,
and you are not abstract, then you should implement
it as follows:
public Object clone() { try { return super.clone(); } catch ((CloneNotSupportedException e) { throw new InternalError(); } // never happens } - If no ancestor of yours implements clone(), but you
need to deep-clone some things, then you should implement it
as follows:
public Object clone() { try { MyObject myobj = (MyObject) (super.clone()); // put your deep-cloning code here... } catch ((CloneNotSupportedException e) { throw new InternalError(); } // never happens return myobj; } - If an ancestor has implemented clone(), and you also need
to deep clone some things, then you should implement it as follows:
public Object clone() { MyObject myobj = (MyObject) (super.clone()); // put your deep-cloning code here... return myobj; }
-
equals
-
flush
public void flush() -
activate
Activates the net such that all outputs are active. -
addInput
Add a new input node. -
addOutput
Add a new output node. -
loadSensors
public void loadSensors(double[] vals) Takes an array of sensor values and loads it into SENSOR inputs ONLY. -
getOutputResults
public double[] getOutputResults()Produces an array of activation results, one per output node. -
hasPath
public static boolean[] hasPath(EvolutionState state, NEATNode toNode, NEATNode fromNode, int threshold) This checks a POTENTIAL link between start from fromNode to toNode to use count and threshold to jump out in the case of an infinite loop. -
hasPath
public static void hasPath(EvolutionState state, NEATNode toNode, NEATNode fromNode, HashSet<NEATNode> set, int level, int threshold, boolean[] results) The helper function to check if there is a path from fromNode to toNode. -
outputOff
public boolean outputOff()Check if not all output are active. -
maxDepth
public int maxDepth()Find the maximum number of neurons between an output and an input. -
buildNetwork
Create the phenotype (network) from the genotype (genome). One main task of method is to link the incomingGenes for each nodes.
-