python - 创建大量对象(神经元)并使用字典随机连接

Question

我正在实验性地尝试创建一种具有以下标准的新型神经网络:

• 每个神经元必须是一个单独的对象。
• 每个神经元都应该有自己的线程。
• 网络必须部分连接且随机(在启动时)。
• 神经元必须异步运行以计算其输出、更新其权重等。

这些是我在 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
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)

Julia

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，这些部分在每个神经元之间部分随机地建立连接，花费太多时间。 我怎样才能加快这个过程/部分？

python

def build_connections(self):
    for neuron in Neuron.neurons:
        self.n += 1
        #neuron.thread.start()
        neuron.partially_connect()
        print "Counter: " + str(self.n)

Julia

n = 0
@parallel for neuron in neurons
    n += 1
    partially_connect(neuron)
    println("Counter: ",n)

其次，当我的目标是创建至少一百万个神经元时，为每个神经元提供自己的线程是否是个好主意 ？这意味着它将像一个万线程。

我在这里试图做的是严格意义上模仿生物神经网络，而不是使用矩阵计算。

添加:

partially_connect 函数的新版本根据答案:

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))

性能显着提高。

Answer 1

在 Julia 中，如果性能很重要:不要使用全局变量(请参阅您的 neurons 数组)并且不要使用无类型数组(同样，请参阅您的 neurons 数组) .查看performance tips .您还应该分析以确定您的瓶颈在哪里。我强烈建议您在没有 @parallel 的情况下尝试它，直到您可以快速获得它。

我自己看了看，除了这些我还发现了一些令人吃惊的瓶颈:

• rand(1:neuron_count/100) 创建浮点范围，而不是整数范围。这是一个巨大的瓶颈，分析立即识别出来。使用 rand(1:neuron_count÷100)。
• 最好不要调用 object_id，只需使用 !(neuron === self)。或者甚至更好，将神经元作为数组和要修改的条目的整数索引传递。

修复这些项目后，我设法将程序的执行时间从大约 140 秒到 4 秒。几乎所有的运行时间都只是花在生成随机数上；您可以通过一次生成一个大型池而不是一个一个地生成它们来加速这一过程。

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()