def __init__(self,
chromosome,
maxNIndividuals,
valueInitializer=Randomization(-0.1, 0.1),
**kwargs):
""" :key chromosome: The prototype chromosome
:key maxNIndividuals: The maximum allowed number of individuals
"""
SimplePopulation.__init__(self)
self._prototype = EvolinoSubIndividual(chromosome)
self._maxNIndividuals = maxNIndividuals
self._valueInitializer = valueInitializer
self.setArgs(**kwargs)
for _ in range(maxNIndividuals):
self.addIndividual(self._prototype.copy())
self._valueInitializer.apply(self)
class EvolinoSubPopulation(SimplePopulation):
""" The class for Evolino subpopulations. Mostly the same as SimplePopulation
but with a few extensions.
It contains a set of EvolinoSubIndividuals.
On initialization, a prototype individual is created from the prototype
chromosome. This individual is then cloned and added so that the
population exists of maxNIndividuals individuals.
The genomes of these clones are then randomized by the Randomization
operator.
"""
def __init__(self, chromosome, maxNIndividuals, valueInitializer=Randomization(-0.1, 0.1), **kwargs):
""" :key chromosome: The prototype chromosome
:key maxNIndividuals: The maximum allowed number of individuals
"""
SimplePopulation.__init__(self)
self._prototype = EvolinoSubIndividual(chromosome)
self._maxNIndividuals = maxNIndividuals
self._valueInitializer = valueInitializer
self.setArgs(**kwargs)
for _ in range(maxNIndividuals):
self.addIndividual(self._prototype.copy())
self._valueInitializer.apply(self)
def setArgs(self, **kwargs):
for key, val in kwargs.iteritems():
getattr(self, key)
setattr(self, key, val)
def getMaxNIndividuals(self):
""" Returns the maximum allowed number of individuals """
return self._maxNIndividuals
def addIndividualFitness(self, individual, fitness):
""" Add fitness to the individual's fitness value.
:key fitness: a float value denoting the fitness
"""
self._fitness[individual] += fitness
class EvolinoSubPopulation(SimplePopulation):
""" The class for Evolino subpopulations. Mostly the same as SimplePopulation
but with a few extensions.
It contains a set of EvolinoSubIndividuals.
On initialization, a prototype individual is created from the prototype
chromosome. This individual is then cloned and added so that the
population exists of maxNIndividuals individuals.
The genomes of these clones are then randomized by the Randomization
operator.
"""
def __init__(self,
chromosome,
maxNIndividuals,
valueInitializer=Randomization(-0.1, 0.1),
**kwargs):
""" :key chromosome: The prototype chromosome
:key maxNIndividuals: The maximum allowed number of individuals
"""
SimplePopulation.__init__(self)
self._prototype = EvolinoSubIndividual(chromosome)
self._maxNIndividuals = maxNIndividuals
self._valueInitializer = valueInitializer
self.setArgs(**kwargs)
for _ in range(maxNIndividuals):
self.addIndividual(self._prototype.copy())
self._valueInitializer.apply(self)
def setArgs(self, **kwargs):
for key, val in list(kwargs.items()):
getattr(self, key)
setattr(self, key, val)
def getMaxNIndividuals(self):
""" Returns the maximum allowed number of individuals """
return self._maxNIndividuals
def addIndividualFitness(self, individual, fitness):
""" Add fitness to the individual's fitness value.
:key fitness: a float value denoting the fitness
"""
self._fitness[individual] += fitness
def __init__(self, chromosome, maxNIndividuals, valueInitializer=Randomization(-0.1, 0.1), **kwargs):
""" :key chromosome: The prototype chromosome
:key maxNIndividuals: The maximum allowed number of individuals
"""
SimplePopulation.__init__(self)
self._prototype = EvolinoSubIndividual(chromosome)
self._maxNIndividuals = maxNIndividuals
self._valueInitializer = valueInitializer
self.setArgs(**kwargs)
for _ in range(maxNIndividuals):
self.addIndividual(self._prototype.copy())
self._valueInitializer.apply(self)
def __init__(self, evolino_network, dataset, **kwargs):
"""
:key subPopulationSize: Size of the subpopulations.
:key nCombinations: Number of times each chromosome is built into an individual. default=1
:key nParents: Number of individuals left in a subpopulation after selection.
:key initialWeightRange: Range of the weights of the RNN after initialization. default=(-0.1,0.1)
:key weightInitializer: Initializer object for the weights of the RNN. default=Randomization(...)
:key mutationAlpha: The mutation's intensity. default=0.01
:key mutationVariate: The variate used for mutation. default=CauchyVariate(...)
:key wtRatio: The quotient: washout-time/training-time. Needed to
split the sequences into washout phase and training phase.
:key nBurstMutationEpochs: Number of epochs without increase of fitness in a row,
before burstmutation is applied. default=Infinity
:key backprojectionFactor: Weight of the backprojection. Usually
supplied through evolino_network.
:key selection: Selection object for evolino
:key reproduction: Reproduction object for evolino
:key burstMutation: BurstMutation object for evolino
:key evaluation: Evaluation object for evolino
:key verbosity: verbosity level
"""
Trainer.__init__(self, evolino_network)
self.network = evolino_network
self.setData(dataset)
ap = KWArgsProcessor(self, kwargs)
# misc
ap.add('verbosity', default=0)
# population
ap.add('subPopulationSize', private=True, default=8)
ap.add('nCombinations', private=True, default=4)
ap.add('nParents', private=True, default=None)
ap.add('initialWeightRange', private=True, default=(-0.1, 0.1))
ap.add('weightInitializer', private=True, default=Randomization(self._initialWeightRange[0], self._initialWeightRange[1]))
# mutation
ap.add('mutationAlpha', private=True, default=0.01)
ap.add('mutationVariate', private=True, default=CauchyVariate(0, self._mutationAlpha))
# evaluation
ap.add('wtRatio', private=True, default=(1, 3))
# burst mutation
ap.add('nBurstMutationEpochs', default=Infinity)
# network
ap.add('backprojectionFactor', private=True, default=float(evolino_network.backprojectionFactor))
evolino_network.backprojectionFactor = self._backprojectionFactor
# aggregated objects
ap.add('selection', default=EvolinoSelection())
ap.add('reproduction', default=EvolinoReproduction(mutationVariate=self.mutationVariate))
ap.add('burstMutation', default=EvolinoBurstMutation())
ap.add('evaluation', default=EvolinoEvaluation(evolino_network, self.ds, **kwargs))
self.selection.nParents = self.nParents
self._population = EvolinoPopulation(
EvolinoSubIndividual(evolino_network.getGenome()),
self._subPopulationSize,
self._nCombinations,
self._weightInitializer
)
filters = []
filters.append(self.evaluation)
filters.append(self.selection)
filters.append(self.reproduction)
self._filters = filters
self.totalepochs = 0
self._max_fitness = self.evaluation.max_fitness
self._max_fitness_epoch = self.totalepochs
