def fire(self):
# X = αX + (1-α)[WI*I + W*X]
X = plus(times(X, self.alpha),
times(plus(dot(WI, I), dot(W, X)), 1 - self.alpha))
X = tanh(X) #sigmoid(X)
# Y = WO*X
Y = dot(WO, X)
def fire(self):
# X = αX + (1-α)[WI*I + W*X]
self.X = plus(
times(self.X, self.alpha),
times(plus(dot(self.WI, [1] + self.I), dot(self.W, [1] + self.X)),
1 - self.alpha))
self.X = tanh(self.X)
# Y = WO*X
self.Y = dot(self.WO, [1] + self.X)
def ljapexp(q=150, iterations=40, gamma0=10**-8, sigma=0.1):
# input, hidden and output layer size
p = 1
#q = 150
r = 1 #300
# strength of input activations
INPUT_STRENGTH = 10**0
def input_dist():
return INPUT_STRENGTH*uniform(-1,1)
def normgen(mu, sigma):
def n():
return normalvariate(mu, sigma)
return n
def unigen(a,b):
def u():
return uniform(a,b)
return u
def zerogen():
def zero():
return 0
return zero
# matrix and initial activation randomization
r = Reservoir(p, q, r)
r.randomize_matrices(normgen(0,1))
r.WI = random_matrix(q,p+1, unigen(-0.1,0.1))
r.W = random_matrix(q,q+1, normgen(0,sigma))
#r.randomize_vectors(normgen(0,1))
# make a copy of the reservoir
r2 = copy.deepcopy(r)
#perturbation = random_vector(q)
#perturbation = times(perturbation, gamma0 / vector_len(perturbation))
priemersum = 0
for perturbed_node in range(q):
r.randomize_vectors(normgen(0,1))
perturbation = [0 for _ in range(q)]
perturbation[perturbed_node] = gamma0
r2.X = plus(r2.X, perturbation)
difvec = plus(times(r.X, -1), r2.X)
exponentsum = 0
lambdy = [0]*iterations
for it in range(0, iterations):
# introduce a random input
r.I = random_vector(r.p, input_dist)
r2.I = r.I
# run one setp
r.fire()
r2.fire()
# calculate the difference
difvec = plus(times(r.X, -1), r2.X)
gammaK = vector_len(difvec)
# renormalize
r2.X = plus(r.X, times(difvec, gamma0 / gammaK))
# record lambda
mylog = math.log(gammaK / gamma0)
lambdy[it] = mylog
priemer = sum(lambdy) / iterations
disperzia = sum([ (x-priemer)*(x-priemer) for x in lambdy]) / iterations
priemersum += priemer
print("\rnodeindex=%d" % perturbed_node, end="")
return priemersum / q
r.WI = random_matrix(q, p + 1, unigen(-0.1, 0.1))
r.W = random_matrix(q, q + 1, normgen(0, 10**(-0.8)))
r.randomize_vectors(normgen(0, 1))
# make a copy of the reservoir
r2 = copy.deepcopy(r)
#perturbation = random_vector(q)
#perturbation = times(perturbation, gamma0 / vector_len(perturbation))
perturbation = [0] * q
perturbation[randrange(q)] = gamma0
#print(perturbation)
r2.X = plus(r2.X, perturbation)
difvec = plus(times(r.X, -1), r2.X)
#print("difvec = %s" % difvec)
f = open('output.dat', 'w')
exponentsum = 0
lambdy = [0] * ITERATIONS
for it in range(0, ITERATIONS):
r.I = random_vector(r.p, input_dist)
r2.I = r.I
r.fire()
r2.fire()
difvec = plus(times(r.X, -1), r2.X)
gammaK = vector_len(difvec)
r2.X = plus(r.X, times(difvec, gamma0 / gammaK))
mylog = math.log(gammaK / gamma0)
def fire(self): # X = αX + (1-α)[WI*I + W*X] self.X = plus(times(self.X, self.alpha), times(plus( dot(self.WI, [1]+self.I), dot(self.W,[1]+self.X)), 1 - self.alpha)) self.X = tanh(self.X) # Y = WO*X self.Y = dot(self.WO, [1]+self.X)
def ljapexp(q=150, iterations=40, gamma0=10**-8, sigma=0.1):
# input, hidden and output layer size
p = 1
#q = 150
r = 1 #300
# strength of input activations
INPUT_STRENGTH = 10**0
def input_dist():
return INPUT_STRENGTH * uniform(-1, 1)
def normgen(mu, sigma):
def n():
return normalvariate(mu, sigma)
return n
def unigen(a, b):
def u():
return uniform(a, b)
return u
def zerogen():
def zero():
return 0
return zero
# matrix and initial activation randomization
r = Reservoir(p, q, r)
r.randomize_matrices(normgen(0, 1))
r.WI = random_matrix(q, p + 1, unigen(-0.1, 0.1))
r.W = random_matrix(q, q + 1, normgen(0, sigma))
#r.randomize_vectors(normgen(0,1))
# make a copy of the reservoir
r2 = copy.deepcopy(r)
#perturbation = random_vector(q)
#perturbation = times(perturbation, gamma0 / vector_len(perturbation))
priemersum = 0
for perturbed_node in range(q):
r.randomize_vectors(normgen(0, 1))
perturbation = [0 for _ in range(q)]
perturbation[perturbed_node] = gamma0
r2.X = plus(r2.X, perturbation)
difvec = plus(times(r.X, -1), r2.X)
exponentsum = 0
lambdy = [0] * iterations
for it in range(0, iterations):
# introduce a random input
r.I = random_vector(r.p, input_dist)
r2.I = r.I
# run one setp
r.fire()
r2.fire()
# calculate the difference
difvec = plus(times(r.X, -1), r2.X)
gammaK = vector_len(difvec)
# renormalize
r2.X = plus(r.X, times(difvec, gamma0 / gammaK))
# record lambda
mylog = math.log(gammaK / gamma0)
lambdy[it] = mylog
priemer = sum(lambdy) / iterations
disperzia = sum([(x - priemer) * (x - priemer)
for x in lambdy]) / iterations
priemersum += priemer
print("\rnodeindex=%d" % perturbed_node, end="")
return priemersum / q
r.WI = random_matrix(q,p+1, unigen(-0.1,0.1))
r.W = random_matrix(q,q+1, normgen(0,10**(-0.8)))
r.randomize_vectors(normgen(0,1))
# make a copy of the reservoir
r2 = copy.deepcopy(r)
#perturbation = random_vector(q)
#perturbation = times(perturbation, gamma0 / vector_len(perturbation))
perturbation = [0]*q
perturbation[randrange(q)] = gamma0
#print(perturbation)
r2.X = plus(r2.X, perturbation)
difvec = plus(times(r.X, -1), r2.X)
#print("difvec = %s" % difvec)
f = open('output.dat','w')
exponentsum = 0
lambdy = [0]*ITERATIONS
for it in range(0, ITERATIONS):
r.I = random_vector(r.p, input_dist)
r2.I = r.I
r.fire()
r2.fire()
difvec = plus(times(r.X, -1), r2.X)
gammaK = vector_len(difvec)
r2.X = plus(r.X, times(difvec, gamma0 / gammaK))
mylog = math.log(gammaK / gamma0)