def test_spike_integrator(self):
n1 = nef.ScalarNode()
n1.configure(neurons=30, t_ref=0.002, t_rc=0.02)
n1.configure_spikes(pstc=0.02, dt=0.001)
n2 = nef.ScalarNode()
n0 = nef.ScalarNode()
n0.connect(n1, weight=0.02 * 3.1415 * 2)
n1.connect(n1)
n1.connect(n2)
t = numpy.arange(1000) * n1.dt
input = numpy.cos(3.1415 * t * 2)
vv = []
for i in xrange(1000):
n0.set(input[i])
n1.tick()
vv.append(n2.value())
#if i%50==0: print i,n1.value(),n2.value()
self.assertTrue(vv[250] > 0.8)
self.assertTrue(abs(vv[500]) < 0.2)
self.assertTrue(vv[750] < -0.8)
self.assertTrue(abs(vv[999]) < 0.2)
import pylab
pylab.plot(t, vv)
pylab.plot(t, input)
pylab.show()
def test_linear_weights(self):
n1 = nef.ScalarNode(noise=0)
n2 = nef.ScalarNode(noise=0)
n1.connect(n2)
n1.set(0.3)
n1.tick()
n1.tick()
self.assertEqual(n2.value(), 0.3)
n1.set(-0.7)
n1.tick()
n1.tick()
self.assertEqual(n2.value(), -0.7)
for w in [-1, -10, 0, 0.5, 0.2]:
n1 = nef.ScalarNode(noise=0)
n2 = nef.ScalarNode(noise=0)
n1.connect(n2, weight=w)
n1.set(0.3)
n1.tick()
n1.tick()
self.assertEqual(n2.value(), 0.3 * w)
n1.set(-0.7)
n1.tick()
n1.tick()
self.assertEqual(n2.value(), -0.7 * w)
def test_connection(self):
n1=nef.ScalarNode(noise=0)
n2=nef.ScalarNode(noise=0)
n1.connect(n2)
n1.set(0.3)
n1.tick()
n1.tick()
self.assertEqual(n2.value(),0.3)
n1.set(-0.7)
n1.tick()
n1.tick()
self.assertEqual(n2.value(),-0.7)
n1=nef.VectorNode(2,noise=0)
n2=nef.VectorNode(2,noise=0)
n1.connect(n2,weight=0.1)
n1.set([0.3,-0.7])
n1.tick()
n1.tick()
self.assertAlmostEqual(n2.value()[0],0.03)
self.assertAlmostEqual(n2.value()[1],-0.07)
n1=nef.VectorNode(2,noise=0)
n2=nef.VectorNode(2,noise=0)
n1.connect(n2,weight=numpy.array([[0,1],[1,0]]))
n1.set([0.3,-0.7])
n1.tick()
n1.tick()
self.assertEqual(n2.value()[0],-0.7)
self.assertEqual(n2.value()[1],0.3)
def test_connection(self):
modes = ['direct', 'rate']
for m1 in modes:
for m2 in modes:
#print m1,m2
n1 = nef.ScalarNode()
if m1 == 'rate':
n1.configure(neurons=150, activation_noise=0.01)
n2 = nef.ScalarNode()
if m2 == 'rate':
n2.configure(neurons=150, activation_noise=0.01)
n1.connect(n2)
n1.set(0.3)
n1.tick()
n1.tick()
#print 0.3,n2.value()
self.assertAlmostEqual(n2.value(), 0.3, 1)
n1.set(-0.7)
n2.tick()
n2.tick()
#print -0.7,n2.value()
self.assertAlmostEqual(n2.value(), -0.7, 1)
n1 = nef.VectorNode(2, noise=0)
if m1 == 'rate':
n1.configure(neurons=300,
activation_noise=0.01,
basis_style='Aligned')
n2 = nef.VectorNode(2, noise=0, min=-0.5, max=0.5)
if m2 == 'rate':
n2.configure(neurons=300,
activation_noise=0.01,
basis_style='Aligned')
n1.connect(n2, weight=0.5)
n1.set([0.3, -0.7])
n2.tick()
n2.tick()
#print [0.15,-0.35],n2.value()
self.assertAlmostEqual(n2.value()[0], 0.15, 2)
self.assertAlmostEqual(n2.value()[1], -0.35, 2)
n1 = nef.VectorNode(2, noise=0)
if m1 == 'rate':
n1.configure(neurons=300,
activation_noise=0.01,
basis_style='Aligned')
n2 = nef.VectorNode(2, noise=0)
if m2 == 'rate':
n2.configure(neurons=300,
activation_noise=0.01,
basis_style='Aligned')
n1.connect(n2, weight=numpy.array([[0, 1], [1, 0]]))
n1.set([0.3, -0.7])
n1.tick()
n1.tick()
#print [-0.7,0.3],n2.value()
self.assertAlmostEqual(n2.value()[0], -0.7, 1)
self.assertAlmostEqual(n2.value()[1], 0.3, 1)
def test_collection(self):
n=nef.CollectionNode(nef.ScalarNode(),nef.VectorNode(3),nef.ScalarNode(),noise=0)
v1=[0.3,[0.2,0.1,-0.5],-1.0]
n.set(v1)
n.tick()
v2=n.value()
self.assertEqual(v1[0],v2[0])
self.assertEqual(v1[1][0],v2[1][0])
self.assertEqual(v1[1][1],v2[1][1])
self.assertEqual(v1[1][2],v2[1][2])
self.assertEqual(v1[2],v2[2])
def test_linear_weights_n(self):
n1 = nef.ScalarNode()
n1.configure(neurons=200, activation_noise=0.01)
n2 = nef.ScalarNode()
n1.configure(neurons=200, activation_noise=0.01)
n1.connect(n2)
n1.set(0.3)
n1.tick()
n1.tick()
self.assertAlmostEqual(n2.value(), 0.3, 1)
n1.set(-0.7)
n1.tick()
n1.tick()
self.assertAlmostEqual(n2.value(), -0.7, 1)
def test_many_connections1(self):
out = nef.ScalarNode(noise=0)
N = 10
n = [nef.ScalarNode(noise=0) for i in range(N)]
for i in range(N):
n[i].configure(neurons=150, activation_noise=0.01)
if i + 1 < N:
n[i].connect(n[i + 1])
n[i].connect(out)
n[0].set(1)
out.tick()
for i in range(N):
out.tick()
self.assertAlmostEqual(out.value(), i + 1, 0)
out.tick()
self.assertAlmostEqual(out.value(), N, 0)
def test_add(self):
samples = None
a = nef.ScalarNode()
b = nef.ScalarNode()
c = nef.ScalarNode()
a.configure(neurons=150,
activation_noise=0.1,
apply_noise=False,
sample_count=samples)
b.configure(neurons=150,
activation_noise=0.1,
apply_noise=False,
sample_count=samples)
c.configure(neurons=150,
activation_noise=0.1,
apply_noise=False,
sample_count=samples)
a.connect(c)
b.connect(c)
ab = nef.VectorNode(2)
a.connect(ab, weight=numpy.array([1, 0]))
b.connect(ab, weight=numpy.array([0, 1]))
ab.configure(neurons=300,
activation_noise=0.1,
apply_noise=False,
sample_count=samples)
c2 = nef.ScalarNode()
c2.configure(neurons=150,
activation_noise=0.1,
apply_noise=False,
sample_count=samples)
ab.connect(c2, func=lambda x: x[0] + x[1])
n = [-0.4, -0.3, -0.1, 0, 0.1, 0.3, 0.4]
for x in n:
for y in n:
a.set(x)
b.set(y)
c.tick()
c.tick()
c.tick()
self.assertAlmostEqual(x + y, c.value(), 1)
self.assertAlmostEqual(x + y, c2.value(), 1)
def _test_spike_connect_d_s_d(self):
a=nef.ScalarNode(noise=0)
b=nef.ScalarNode()
c=nef.ScalarNode(noise=0)
b.configure(neurons=30,apply_noise=False)
b.configure_spikes(pstc=0.03)
a.set(-0.3)
a.connect(b)
b.connect(c)
N=2000
for i in range(N):
b.tick()
if i%100==99: print (i+1),c.value()
self.assertAlmostEqual(a.value(),c.value(),1)
self.assertAlmostEqual(a.value(),c.value(),1)
def test_accuracy(self):
n = nef.ScalarNode(noise=0)
n.configure(neurons=150, activation_noise=0.01, apply_noise=False)
vals = numpy.arange(30) / 15.0 - 1
for v in vals:
n.set(v)
n.tick()
#print v,n.value()
self.assertAlmostEqual(n.value(), v, 1)
def test_many_connections2(self):
out = nef.ScalarNode(noise=0)
out.configure(neurons=150, activation_noise=0.1, apply_noise=False)
N = 10
n = [nef.ScalarNode(noise=0) for i in range(N)]
for i in range(N):
n[i].configure(neurons=150,
activation_noise=0.1,
apply_noise=False)
if i + 1 < N:
n[i].connect(n[i + 1])
n[i].connect(out, weight=1.0 / N)
n[0].set(1)
out.tick()
for i in range(N):
out.tick()
self.assertAlmostEqual(out.value() * N, i + 1, 0)
out.tick()
self.assertAlmostEqual(out.value() * N, N, 0)
def test_representation(self):
n1 = nef.ScalarNode()
n1.configure(neurons=150, activation_noise=0.01)
n1.set(0.3)
n1.tick()
self.assertAlmostEqual(n1.value(), 0.3, 2)
n2 = nef.VectorNode(2)
n2.configure(neurons=200, activation_noise=0)
n2.set([0.3, -0.5])
n2.tick()
self.assertAlmostEqual(n2.value()[0], 0.3, 1)
self.assertAlmostEqual(n2.value()[1], -0.5, 1)
def _test_spike_rate(self):
n=nef.ScalarNode()
n.configure(neurons=1,t_ref=0.002,t_rc=0.02)
n.alpha[:]=3.34179049952
n.Jbias[:]=1.46335060944
n.basis[:]=1
n.configure_spikes()
n.set(1)
total=0
for i in range(10000):
n.tick()
if n._output[0]>=0:
total+=1
self.assertEqual(40,total)
from ccm.lib import nef
import numpy
# Adjust these values to change the matrix dimensions
# Matrix A is D1xD2
# Matrix B is D2xD3
# result is D1xD3
D1 = 5
D2 = 5
D3 = 5
pstc = 0.01
dt = 0.001
A = [nef.ScalarNode() for i in range(D1 * D2)]
B = [nef.ScalarNode() for i in range(D2 * D3)]
for n in A + B:
n.configure(neurons=50)
n.configure_spikes(pstc=pstc, dt=dt)
# the C matrix holds the intermediate product calculations
# need to compute D1*D2*D3 products to multiply 2 matrices together
C = [nef.VectorNode(2) for i in range(D1 * D2 * D3)]
for n in C:
n.configure(neurons=200)
n.configure_spikes(pstc=pstc, dt=dt)
# determine the transformation matrices to get the correct pairwise
# products computed. This looks a bit like black magic but if
