def fully_connected_nn(n_inputs, n_outputs):
"""Generate a genotype representing a fully connected neural network.
Arguments:
n_inputs: How many inputs the network should have.
n_outputs: How many outputs the network should have.
Returns: The generated genotype.
"""
genome = Genome()
sensors = [NodeGene(Sensor()) for _ in range(n_inputs)]
outputs = [NodeGene(Output()) for _ in range(n_outputs)]
connections = []
for input_id in range(n_inputs):
for output_id in range(n_inputs, n_inputs + n_outputs):
connections.append(ConnectionGene(output_id, input_id))
genome.add_genes(sensors)
genome.add_genes(outputs)
genome.add_genes(connections)
return genome
def generate_genome():
"""Generate a test genome.
Returns a genotype similar to one found in the origin NEAT paper.
"""
ConnectionGene.pool = {}
genome = Genome()
nodes = [NodeGene(Sensor()) for _ in range(3)]
nodes.append(NodeGene(Output()))
nodes.append(NodeGene(Hidden()))
connections = []
for input_node_id in [0, 2, 4]:
connections.append(ConnectionGene(3, input_node_id))
for input_node_id in [0, 1, 3]:
connections.append(ConnectionGene(4, input_node_id))
genome.add_genes(nodes)
genome.add_genes(connections)
return genome