def test_noise(Simulator, nl_nodirect, seed, plt):
"""Ensure that setting Ensemble.noise generates noise."""
with nengo.Network(seed=seed) as model:
inp, gain, bias = 1, 5, 2
neg_noise, pos_noise = -4, 20
model.config[nengo.Ensemble].neuron_type = nl_nodirect()
model.config[nengo.Ensemble].encoders = Choice([[1]])
model.config[nengo.Ensemble].gain = Choice([gain])
model.config[nengo.Ensemble].bias = Choice([bias])
const = nengo.Node(output=inp)
pos = nengo.Ensemble(
1, 1, noise=StochasticProcess(Choice([pos_noise])))
normal = nengo.Ensemble(1, 1)
neg = nengo.Ensemble(
1, 1, noise=StochasticProcess(Choice([neg_noise])))
nengo.Connection(const, pos)
nengo.Connection(const, normal)
nengo.Connection(const, neg)
pos_p = nengo.Probe(pos.neurons, synapse=0.1)
normal_p = nengo.Probe(normal.neurons, synapse=0.1)
neg_p = nengo.Probe(neg.neurons, synapse=0.1)
sim = Simulator(model)
sim.run(0.06)
t = sim.trange()
plt.title("input=%d, bias=%d, gain=%d" % (inp, bias, gain))
plt.plot(t, sim.data[pos_p], c='b', label="noise=%d" % pos_noise)
plt.plot(t, sim.data[normal_p], c='k', label="no noise")
plt.plot(t, sim.data[neg_p], c='r', label="noise=%d" % neg_noise)
plt.legend(loc="best")
assert np.all(sim.data[pos_p] >= sim.data[normal_p])
assert np.all(sim.data[normal_p] >= sim.data[neg_p])
assert not np.all(sim.data[normal_p] == sim.data[pos_p])
assert not np.all(sim.data[normal_p] == sim.data[neg_p])
def test_stochasticprocess(rng):
dist = DistributionMock(42)
process = StochasticProcess(dist)
samples = nengo.processes.sample(5, process, d=2, rng=rng)
assert np.all(samples == 42 * np.ones((5, 2)))
assert nengo.processes.sample(5, process).shape == (5, )
assert nengo.processes.sample(1, process, d=1).shape == (1, 1)
assert nengo.processes.sample(2, process, d=3).shape == (2, 3)
def test_gaussian_whitenoise(rms, rng, plt):
d = 500
t = 100
dt = 0.001
process = StochasticProcess(Gaussian(0., rms))
values = nengo.processes.sample(t, process, dt=dt, d=d, rng=rng)
freq, val_psd = psd(values)
trange = np.arange(1, t + 1) * dt
plt.subplot(2, 1, 1)
plt.title("First two dimensions of white noise process, rms=%.1f" % rms)
plt.plot(trange, values[:, :2])
plt.xlim(right=trange[-1])
plt.subplot(2, 1, 2)
plt.title("Power spectrum")
plt.plot(freq, val_psd, drawstyle='steps')
assert np.allclose(np.std(values), rms, rtol=0.02)
assert np.allclose(val_psd[1:-1], rms, rtol=0.2)
def test_noise_copies_ok(Simulator, nl_nodirect, seed, plt):
"""Make sure the same noise process works in multiple ensembles.
We test this both with the default system and without.
"""
process = StochasticProcess(Choice([0.5]), synapse=nengo.Alpha(1.))
with nengo.Network(seed=seed) as model:
inp, gain, bias = 1, 5, 2
model.config[nengo.Ensemble].neuron_type = nl_nodirect()
model.config[nengo.Ensemble].encoders = Choice([[1]])
model.config[nengo.Ensemble].gain = Choice([gain])
model.config[nengo.Ensemble].bias = Choice([bias])
model.config[nengo.Ensemble].noise = process
const = nengo.Node(output=inp)
a = nengo.Ensemble(1, 1, noise=process)
b = nengo.Ensemble(1, 1, noise=process)
c = nengo.Ensemble(1, 1) # defaults to noise=process
nengo.Connection(const, a)
nengo.Connection(const, b)
nengo.Connection(const, c)
ap = nengo.Probe(a.neurons, synapse=0.01)
bp = nengo.Probe(b.neurons, synapse=0.01)
cp = nengo.Probe(c.neurons, synapse=0.01)
sim = Simulator(model)
sim.run(0.06)
t = sim.trange()
plt.subplot(2, 1, 1)
plt.plot(t, sim.data[ap], lw=3)
plt.plot(t, sim.data[bp], lw=2)
plt.plot(t, sim.data[cp])
plt.subplot(2, 1, 2)
plt.plot(*nengo.utils.ensemble.tuning_curves(a, sim), lw=3)
plt.plot(*nengo.utils.ensemble.tuning_curves(b, sim), lw=2)
plt.plot(*nengo.utils.ensemble.tuning_curves(c, sim))
assert np.allclose(sim.data[ap], sim.data[bp])
assert np.allclose(sim.data[bp], sim.data[cp])