def gaussian_activation(self):
x = self.dists
radii = zeros(self.dists.shape) * 0.0
for u,conn_dict in enumerate(self.connections):
neighbors = take(self.weights,conn_dict.keys())
radii[u] = average(matrixnorm(neighbors-self.weights[u]))
self.__activation = gaussian(x,radii/2)
def find_in_radius(self,key,radius):
if not self.db:
return [],[]
X = array([x for x,v in self.db])
dists = matrixnorm(key-X)
close_enough = nonzero(dists <= radius)
return ([self.db[i] for i in close_enough],
[dists[i] for i in close_enough])
def gaussian_activation(self):
x = self.dists
radii = zeros(self.dists.shape) * 0.0
for u, conn_dict in enumerate(self.connections):
neighbors = take(self.weights, conn_dict.keys())
radii[u] = average(matrixnorm(neighbors - self.weights[u]))
self.__activation = gaussian(x, radii / 2)
def uniform_gaussian_activation(self):
x = self.dists
total = 0.0
count = 0
for u,conn_dict in enumerate(self.connections):
neighbors = take(self.weights,conn_dict.keys())
total += sum(matrixnorm(neighbors-self.weights[u]))
count += len(conn_dict)
self.__activation = gaussian(x,(total/count)/2)
def uniform_gaussian_activation(self):
x = self.dists
total = 0.0
count = 0
for u, conn_dict in enumerate(self.connections):
neighbors = take(self.weights, conn_dict.keys())
total += sum(matrixnorm(neighbors - self.weights[u]))
count += len(conn_dict)
self.__activation = gaussian(x, (total / count) / 2)
def k_nearest(self,key,k):
# TODO: These distance computations can be further optimized
# if the keys are stored as a matrix instead of as separate vectors.
# However that would require changes in the VectorTree class, too.
if not self.db:
return [],[]
X = array([x for x,v in self.db])
dists = matrixnorm(key-X)
sorted_indices = argsort(dists)
return ([self.db[i] for i in sorted_indices[:k]],
[dists[i] for i in sorted_indices[:k]])
def any_in_radius(self,key,radius):
if not self.db:
return False
X = array([x for x,v in self.db])
dists = matrixnorm(key-X)
return sometrue(dists <= radius)
def present_input(self,X):
self.dists = matrixnorm(self.weights-X)
self.last_input = X
self.new_input = True
def present_input(self, X):
self.dists = matrixnorm(self.weights - X)
self.last_input = X
self.new_input = True
