12

我想知道是否有人在 python 中有一些神经网络的示例代码。如果有人知道某种带有完整演练的教程,那将是很棒的,但是仅示例源也很棒!

谢谢

4

3 回答 3

4

在 ubuntu 论坛上找到了这个有趣的讨论 http://ubuntuforums.org/showthread.php?t=320257

import time
import random

# Learning rate:
# Lower  = slower
# Higher = less precise
rate=.2

# Create random weights
inWeight=[random.uniform(0, 1), random.uniform(0, 1)]

# Start neuron with no stimuli
inNeuron=[0.0, 0.0]

# Learning table (or gate)
test =[[0.0, 0.0, 0.0]]
test+=[[0.0, 1.0, 1.0]]
test+=[[1.0, 0.0, 1.0]]
test+=[[1.0, 1.0, 1.0]]

# Calculate response from neural input
def outNeuron(midThresh):
    global inNeuron, inWeight
    s=inNeuron[0]*inWeight[0] + inNeuron[1]*inWeight[1]
    if s>midThresh:
        return 1.0
    else:
        return 0.0

# Display results of test
def display(out, real):
        if out == real:
            print str(out)+" should be "+str(real)+" ***"
        else:
            print str(out)+" should be "+str(real)

while 1:
    # Loop through each lesson in the learning table
    for i in range(len(test)):
        # Stimulate neurons with test input
        inNeuron[0]=test[i][0]
        inNeuron[1]=test[i][1]
        # Adjust weight of neuron #1
        # based on feedback, then display
        out = outNeuron(2)
        inWeight[0]+=rate*(test[i][2]-out)
        display(out, test[i][2])
        # Adjust weight of neuron #2
        # based on feedback, then display
        out = outNeuron(2)
        inWeight[1]+=rate*(test[i][2]-out)
        display(out, test[i][2])
        # Delay
        time.sleep(1)

编辑:还有一个名为chainer的框架 https://pypi.python.org/pypi/chainer/1.0.0

于 2012-09-15T10:00:25.490 回答
2

您可能想看看Monte

Monte (python) 是一个 Python 框架,用于构建基于梯度的学习机,如神经网络、条件随机场、逻辑回归等。 Monte 包含模块(保存参数、成本函数和梯度函数)和训练器(可以通过最小化其在训练数据上的成本函数来调整模块的参数)。

模块通常由其他模块组成,这些模块又可以包含其他模块等。像这样的可分解系统的梯度可以通过反向传播来计算。

于 2009-10-04T07:59:46.497 回答
2

这是一个概率神经网络教程:http ://www.youtube.com/watch?v=uAKu4g7lBxU

还有我的 Python 实现:

import math

data = {'o' : [(0.2, 0.5), (0.5, 0.7)],
        'x' : [(0.8, 0.8), (0.4, 0.5)],
        'i' : [(0.8, 0.5), (0.6, 0.3), (0.3, 0.2)]}

class Prob_Neural_Network(object):
    def __init__(self, data):
        self.data = data

    def predict(self, new_point, sigma):
        res_dict = {}
        np = new_point
        for k, v in self.data.iteritems():
            res_dict[k] = sum(self.gaussian_func(np[0], np[1], p[0], p[1], sigma) for p in v)
        return max(res_dict.iteritems(), key=lambda k : k[1])

    def gaussian_func(self, x, y, x_0, y_0, sigma):
        return  math.e ** (-1 *((x - x_0) ** 2 + (y - y_0) ** 2) / ((2 * (sigma ** 2))))

prob_nn = Prob_Neural_Network(data)
res = prob_nn.predict((0.2, 0.6), 0.1)

结果:

>>> res
('o', 0.6132686067117191)
于 2013-08-30T03:19:19.587 回答