Python 创建大量对象(神经元)并使用字典随机连接
我在实验中试图用以下标准创建一种新的神经网络:Python 创建大量对象(神经元)并使用字典随机连接,python,multithreading,neural-network,julia,perceptron,Python,Multithreading,Neural Network,Julia,Perceptron,我在实验中试图用以下标准创建一种新的神经网络: 每个神经元必须是一个独立的对象 每个神经元都应该有自己的线程 网络必须部分随机连接(启动时) 神经元必须异步运行以计算其输出、更新其权重等 以下是我在Julia和Python中的实现尝试: Python import random import itertools import time import signal from threading import Thread from multiprocessing import Pool imp
- 每个神经元必须是一个独立的对象
- 每个神经元都应该有自己的线程
- 网络必须部分随机连接(启动时)
- 神经元必须异步运行以计算其输出、更新其权重等
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)
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
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()
n = 0
@parallel for neuron in neurons
n += 1
partially_connect(neuron)
println("Counter: ",n)
首先,这些部分在每个神经元之间部分地、随机地建立连接,花费了太多的时间。如何加快此过程/部件的速度
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)
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
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()
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,给每个神经元分配自己的线程是个好主意吗?这意味着它将像一百万根线
我在这里试图做的是在严格意义上模仿生物神经网络,而不是使用矩阵计算
添加:
新版本的部分连接
功能符合以下回答:
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))
性能显著提高。看看下面的代码:
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)
根据你对我的评论的回复,这里有几件事:
L[0://code>的语法时,您正在制作列表的副本。slice语法为每个函数调用生成Neuron.neurons
数组的浅拷贝。这是一个O(n)操作,由于在build\u connections
函数中为每个神经元调用partially\u connect
一次,因此它是O(n²)。(哎呀!)
random.paretovariate()
和random.sample()
函数。您可以轻松计算num\u connections=random.paretovariate(1.0)*100
,然后说connected\u nodes=random.sample(神经元,num\u connections)
。从连接的节点中过滤出self
,就完成了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)
(我现在忽略了指纹。)
我不知道如果不迭代所有神经元寻找匹配的id()。我建议您存储对连接对象的引用作为键,并使用权重作为值:
self.connections = [n:round(random.uniform(0.1, 1.0), 2) for n in elected]
当然,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。通过谷歌搜索,我找到了一些旧的电子邮件线程(呵呵!),其中提到405和254等数字是线程创建限制。我没有看到任何文档说“Python线程现在是无限的!”或其他什么,所以我怀疑您必须改变实现解决方案的方式。在Julia中,如果性能重要:不要使用全局变量(请参见神经元
数组),也不要使用非类型数组(再次,请参见神经元
数组)。看。您还应该分析以确定瓶颈所在的位置。我强烈建议您在不使用
@并行的情况下尝试它,直到您能够快速获得它为止
我亲自研究了一下,除此之外,我还发现了一些令人惊讶的瓶颈:
创建浮点范围,而不是整数范围。这是一个巨大的瓶颈,分析立即发现了这一点。使用rand(1:neuron_count/100)
rand(1:neuron\u count÷100)
- 最好不要调用
,只需使用object\u id
。或者更好,将!(神经元===自身)
神经元作为数组和要修改的条目的整数索引传递
@parallel
,并注释掉文本显示之后)。几乎所有的运行时间都只是用来生成随机数;您可以一次生成一个大的池,而不是一个接一个地生成它们,从而加速这一过程
这使用ProgressMeter包(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()
不幸的是,我不能回答你的问题,但我只是一个建议——也许用更少的粗体和斜体字?这有点难读。祝你好运:)是的,你不能做一百万个线程。你为什么要这么做?由于全局解释器锁定,Python无法进入多线程以提高性能。@DonkeyKong感谢您的建议:)这可能是使用tornado或asyncio的微线程(也称为协程)的一个很好的候选。每个神经元都可以通过一些套接字(甚至通过WebSocket)与超星系团通信,它们各自可以运行子协同路由、定期回调等。同样,协同路由可以使大部分代码无阻塞,这意味着您可以将构建连接“延迟”到io_循环,而io_循环将异步执行,让你的for循环非常快。异步编程需要很多时间来理解,但它确实非常强大。祝你好运。
[len(self.connections):]
来自我的旧版本,我忘了删除。我现在删除了,但仍然没有表现上的差异。我如何摆脱O(n²)并使其变得O(n)复杂?不过,我还是不明白。您的第二个语句使用了random.sample()
极大地提高了性能。谢谢!但我