def test_network():
neurons = {0: IFNeuron(5), 1: IFNeuron(10), 2: IFNeuron(20)}
inputs = [0, 1]
outputs = [2]
connections = [(0, 2, 0.123), (1, 2, 0.234)]
net = IFNetwork(neurons, inputs, outputs, connections)
def test_basic():
n = IFNeuron(20)
spike_train = []
for i in range(1000):
spike_train.append(n.potential)
n.advance()
from __future__ import print_function
import matplotlib.pyplot as plt
from neat.ifnn import IFNeuron
n = IFNeuron()
times = []
currents = []
potentials = []
fired = []
for i in range(1000):
times.append(1.0 * i)
n.current = 0.0 if i < 100 or i > 800 else 16.0
currents.append(n.current)
n.advance()
potentials.append(n.potential)
fired.append(1.0 if n.has_fired else 0.0)
plt.subplot(3, 1, 1)
plt.title("IFNN model")
plt.ylabel("Input current")
plt.ylim(0, 20)
plt.grid()
plt.plot(times, currents, "b-", label="current")
plt.subplot(3, 1, 2)
plt.ylabel("Potential")
def test_basic():
n = IFNeuron(20)
spike_train = []
for i in range(1000):
spike_train.append(n.potential)
n.advance()