我正在尝试用这些标准创建一种新的神经网络:
这些是我在Julia和Python中的实现尝试:
的Python
import random
import itertools
import time
import signal
from threading import Thread
from multiprocessing import Pool
import multiprocessing
POTENTIAL_RANGE = 110000 # Resting potential: -70 mV Membrane potential range: +40 mV to -70 mV --- Difference: 110 mV = 110000 microVolt --- https://en.wikipedia.org/wiki/Membrane_potential
ACTION_POTENTIAL = 15000 # Resting potential: -70 mV Action potential: -55 mV --- Difference: 15mV = 15000 microVolt --- https://faculty.washington.edu/chudler/ap.html
AVERAGE_SYNAPSES_PER_NEURON = 8200 # The average number of synapses per neuron: 8,200 --- http://www.ncbi.nlm.nih.gov/pubmed/2778101
# https://en.wikipedia.org/wiki/Neuron
class Neuron():
neurons = []
def __init__(self):
self.connections = {}
self.potential = 0.0
self.error = 0.0
#self.create_connections()
#self.create_axon_terminals()
Neuron.neurons.append(self)
self.thread = Thread(target = self.activate)
#self.thread.start()
#self.process = multiprocessing.Process(target=self.activate)
def fully_connect(self):
for neuron in Neuron.neurons[len(self.connections):]:
if id(neuron) != id(self):
self.connections[id(neuron)] = round(random.uniform(0.1, 1.0), 2)
def partially_connect(self):
if len(self.connections) == 0:
neuron_count = len(Neuron.neurons)
for neuron in Neuron.neurons[len(self.connections):]:
if id(neuron) != id(self):
if random.randint(1,neuron_count/100) == 1:
self.connections[id(neuron)] = round(random.uniform(0.1, 1.0), 2)
print "Neuron ID: " + str(id(self))
print " Potential: " + str(self.potential)
print " Error: " + str(self.error)
print " Connections: " + str(len(self.connections))
def activate(self):
while True:
'''
for dendritic_spine in self.connections:
if dendritic_spine.axon_terminal is not None:
dendritic_spine.potential = dendritic_spine.axon_terminal.potential
print dendritic_spine.potential
self.neuron_potential += dendritic_spine.potential * dendritic_spine.excitement
terminal_potential = self.neuron_potential / len(self.axon_terminals)
for axon_terminal in self.axon_terminals:
axon_terminal.potential = terminal_potential
'''
#if len(self.connections) == 0:
# self.partially_connect()
#else:
self.partially_connect()
pass
'''
if abs(len(Neuron.neurons) - len(self.connections) + 1) > 0:
self.create_connections()
if abs(len(Neuron.neurons) - len(self.axon_terminals) + 1) > 0:
self.create_axon_terminals()
'''
class Supercluster():
def __init__(self,size):
for i in range(size):
Neuron()
print str(size) + " neurons created."
self.n = 0
self.build_connections()
#pool = Pool(4, self.init_worker)
#pool.apply_async(self.build_connections(), arguments)
#map(lambda x: x.partially_connect(),Neuron.neurons)
#map(lambda x: x.create_connections(),Neuron.neurons)
#map(lambda x: x.create_axon_terminals(),Neuron.neurons)
def build_connections(self):
for neuron in Neuron.neurons:
self.n += 1
#neuron.thread.start()
neuron.partially_connect()
print "Counter: " + str(self.n)
Supercluster(10000)
朱莉娅
global neurons = []
type Neuron
connections::Dict{UInt64,Float16}
potential::Float16
error::Float16
function Neuron(arg1,arg2,arg3)
self = new(arg1,arg2,arg3)
push!(neurons, self)
end
end
function fully_connect(self)
for neuron in neurons
if object_id(neuron) != object_id(self)
self.connections[object_id(neuron)] = rand(1:100)/100
#push!(self.connections, rand(1:100)/100)
end
end
end
function partially_connect(self)
if isempty(self.connections)
neuron_count = length(neurons)
for neuron in neurons
if object_id(neuron) != object_id(self)
if rand(1:neuron_count/100) == 1
self.connections[object_id(neuron)] = rand(1:100)/100
#push!(self.connections, rand(1:100)/100)
end
end
end
println("Neuron ID: ",object_id(self))
println(" Potential: ",self.potential)
println(" Error: ",self.error)
println(" Connections: ",length(self.connections))
end
end
function Build()
for i = 1:10000
Neuron(Dict(),0.0,0.0)
end
println(length(neurons), " neurons created.")
n = 0
@parallel for neuron in neurons
n += 1
partially_connect(neuron)
println("Counter: ",n)
end
end
Build()
首先,这些部分正在部分和随机地在每个神经元之间建立连接,花费太多时间。 如何加快此流程/部分?
的Python
def build_connections(self):
for neuron in Neuron.neurons:
self.n += 1
#neuron.thread.start()
neuron.partially_connect()
print "Counter: " + str(self.n)
朱莉娅
n = 0
@parallel for neuron in neurons
n += 1
partially_connect(neuron)
println("Counter: ",n)
其次,当我的目标是创造至少一百万个神经元时,给每个神经元,它自己的线程 是个好主意吗?这意味着它会像一个百万线程。
我在这里要做的是严格意义上的模仿生物神经网络,而不是使用矩阵计算。
此外:
新版partially_connect
功能根据回答:
def partially_connect(self):
if len(self.connections) == 0:
neuron_count = len(Neuron.neurons)
#for neuron in Neuron.neurons:
elected = random.sample(Neuron.neurons,100)
for neuron in elected:
if id(neuron) != id(self):
#if random.randint(1,neuron_count/100) == 1:
self.connections[id(neuron)] = round(random.uniform(0.1, 1.0), 2)
print "Neuron ID: " + str(id(self))
print " Potential: " + str(self.potential)
print " Error: " + str(self.error)
print " Connections: " + str(len(self.connections))
性能急剧提升。
答案 0 :(得分:2)
在Julia中,如果性能很重要:不要使用全局变量(请参阅neurons
数组)并且不要使用无类型数组(再次参见neurons
数组)。请参阅performance tips。您还应该剖析以确定瓶颈所在。我强烈建议您在没有@parallel
的情况下进行尝试,直到您能够快速完成。
我自己看了看,除此之外我发现了一些令人惊讶的瓶颈:
rand(1:neuron_count/100)
创建一个浮点范围,而不是整数范围。这是一个巨大的瓶颈,可以立即识别出分析。使用rand(1:neuron_count÷100)
。object_id
,只需使用!(neuron === self)
。或者甚至更好,将neurons
作为数组和要修改的条目的整数索引传递。修复这些项目,我设法获得程序的执行时间(在删除@parallel
之后,这不太可能有用,并在文本显示中注释掉)从大约140秒到4秒几乎所有的运行时都只是用于生成随机数;您可以通过一次生成一个大型池来加速它,而不是逐个生成它们。
这使用ProgressMeter包(您必须安装)来显示进度。
using ProgressMeter
type Neuron
connections::Dict{UInt64,Float16}
potential::Float16
error::Float16
end
function fully_connect(self, neurons)
for neuron in neurons
if object_id(neuron) != object_id(self)
self.connections[object_id(neuron)] = rand(1:100)/100
#push!(self.connections, rand(1:100)/100)
end
end
end
function partially_connect(self, neurons)
if isempty(self.connections)
neuron_count = length(neurons)
for neuron in neurons
if !(neuron === self)
if rand(1:neuron_count÷100) == 1
self.connections[object_id(neuron)] = rand(1:100)/100
#push!(self.connections, rand(1:100)/100)
end
end
end
# println("Neuron ID: ",object_id(self))
# println(" Potential: ",self.potential)
# println(" Error: ",self.error)
# println(" Connections: ",length(self.connections))
end
end
function Build()
neurons = [Neuron(Dict(),0.0,0.0) for i = 1:10000]
println(length(neurons), " neurons created.")
@showprogress 1 "Connecting neurons..." for neuron in neurons
partially_connect(neuron, neurons)
end
neurons
end
neurons = Build()
答案 1 :(得分:1)
只看这段代码:
def partially_connect(self):
if len(self.connections) == 0:
neuron_count = len(Neuron.neurons)
for neuron in Neuron.neurons[len(self.connections):]:
if id(neuron) != id(self):
if random.randint(1,neuron_count/100) == 1:
self.connections[id(neuron)] = round(random.uniform(0.1, 1.0), 2)
根据你对我对OP的评论的回复,这里有几件事:
使用L[0:]
等语法时,您正在复制列表。切片语法为每个函数调用生成Neuron.neurons
数组的浅表副本。这是 O(n)操作,因为您为partially_connect
函数中的每个神经元调用build_connections
一次,这使得 O(n²)。 (糟糕!)
你正在用Python工作,可以而且应该在库中完成(在C中,我们希望!)。看看例如random.paretovariate()
和random.sample()
函数。您可以轻松计算num_connections = random.paretovariate(1.0) * 100
,然后说connected_nodes = random.sample(neurons, num_connections)
。从self
过滤掉connected_nodes
,您就完成了。
我认为通过消除n²行为和使用内置库例程,可以大大提升性能。
<强> ADDITION 强>
回应您的补充,请考虑以下事项:
def partially_connect(self):
if len(self.connections) == 0:
elected = random.sample(Neuron.neurons,100)
try:
elected.remove(self)
except ValueError:
pass
for neuron in elected:
self.connections[id(neuron)] = round(random.uniform(0.1, 1.0), 2)
(我现在忽略了打印件。)
我不知道如何在不迭代所有寻找id()
值匹配的神经元的情况下从神经元传递到其连接的神经元。我建议您将连接对象的引用存储为键,并使用权重作为值:
self.connections = [n:round(random.uniform(0.1, 1.0), 2) for n in elected]
这假设您需要遍历从源到目标的链接。
至于线程解决方案,我没有一个好的建议。一个小小的谷歌搜索引导我到一些旧的电子邮件线程(嘿!)提到像405和254这样的数字作为线程创建限制。我还没有看到任何文档说“Python线程现在无法使用!”或者其他什么,所以我怀疑你将不得不改变你实施解决方案的方式。