深度学习 —— 多层感知机

最新推荐文章于 2024-08-29 14:55:31 发布

wangli0519

最新推荐文章于 2024-08-29 14:55:31 发布

阅读量8.4k

点赞数 1

分类专栏：深度学习，Theano 文章标签： #Theano #深度学习

深度学习，Theano 专栏收录该内容

10 篇文章 3 订阅

订阅专栏

我们下一个要介绍的结构是单隐藏层的多层感知机（MLP）。MLP可以看成一个输入层由学习到的非线性转化phi进行转化的逻辑回归分类器。这种转化将输入数据投影到线性可分空间。这个中间层被称为隐藏层。单隐藏层使MLP成为通用估算器。但稍后我们会看到使用多隐藏层具有更大的优势，这就是所谓的深度学习。详见Introduction to Multi-Layer Perceptrons (Feedforward Neural Networks)

这里我们同样使用MNIST数据分类举例。

模型

一个单一隐藏层的多层感知机（或人工神经网络—ANN）可以用图表现为：

_images/mlp.png

正式的单一隐藏层的MLP可以表现为： $f: R^D \rightarrowR^L$ ，其中D是输入向量x的大小，L是输出向量f(x)的大小，矩阵表现为： $f(x) = G( b^{(2)} + W^{(2)}( s( b^{(1)} + W^{(1)} x))),$ b是偏差向量，W是权重矩阵，G和s是激活函数。

向量 $h(x) = \Phi(x) = s(b^{(1)} + W^{(1)} x)$ 构成隐藏层。 $W^{(1)} \in R^{D \times D_h}$ 是连接输入向量和隐藏层的权重矩阵。Wi代表输入单元到第i个隐藏单元的权重。一般选择tanh作为s的激活函数，使用 $tanh(a)=(e^a-e^{-a})/(e^a+e^{-a})$ 或者使用逻辑sigmoid函数， $sigmoid(a)=1/(1+e^{-a})$

这里我们使用tanh因为一般它训练速度更快（有时也有利于解决局部最优）。tanh和sigmoid都是标量到标量函数，但通过点积运算向量和张量自然延伸（将向量分解成元素，生成同样大小的向量）。

输出向量通过以下公式得到 $o(x) = G(b^{(2)} + W^{(2)} h(x))$

我们此前在使用逻辑回归区分MNIST数字时提到过这一公式。如前，在多类区分中，通过使用softmax作为G的函数，可以获得类成员的概率。

训练一个MLP，我们学习模型所有的参数，这里我们使用随机梯度下降和批处理。要学习的参数为： $\theta =\{W^{(2)},b^{(2)},W^{(1)},b^{(1)}\}$

梯度 $\partial{\ell}/\partial{\theta}$ 可以使用反向传播算法获得（连续微分的特殊形式），Theano可以自动计算这一微分过程。

从逻辑回归到多层感知机

我们将聚焦单隐藏层的多层感知机。我们从构建一个单隐藏层的类开始。之后只要在此基础之上加一个逻辑回归层就构建了MLP。

class HiddenLayer(object):
    def __init__(self, rng, input, n_in, n_out, W=None, b=None,
                 activation=T.tanh):
        """
        Typical hidden layer of a MLP: units are fully-connected and have
        sigmoidal activation function. Weight matrix W is of shape (n_in,n_out)
        and the bias vector b is of shape (n_out,).

        NOTE : The nonlinearity used here is tanh

        Hidden unit activation is given by: tanh(dot(input,W) + b)

        :type rng: numpy.random.RandomState
        :param rng: a random number generator used to initialize weights

        :type input: theano.tensor.dmatrix
        :param input: a symbolic tensor of shape (n_examples, n_in)

        :type n_in: int
        :param n_in: dimensionality of input

        :type n_out: int
        :param n_out: number of hidden units

        :type activation: theano.Op or function
        :param activation: Non linearity to be applied in the hidden
                           layer
        """
        self.input = input

隐藏层i权重的初始值应当根据激活函数以对称间断的方式取得样本。

对于tanh函数，区间在 $[-\sqrt{\frac{6}{fan_{in}+fan_{out}}},\sqrt{\frac{6}{fan_{in}+fan_{out}}}]$

对于sigmoid函数，区间在 $[-4\sqrt{\frac{6}{fan_{in}+fan_{out}}},4\sqrt{\frac{6}{fan_{in}+fan_{out}}}]$

这种初始化方式保证了在训练早期，每一个神经元在它的激活函数内操作，信息可以便利的向上（输入到输出）或反向（输出到输入）传播。

        # `W` is initialized with `W_values` which is uniformely sampled
        # from sqrt(-6./(n_in+n_hidden)) and sqrt(6./(n_in+n_hidden))
        # for tanh activation function
        # the output of uniform if converted using asarray to dtype
        # theano.config.floatX so that the code is runable on GPU
        # Note : optimal initialization of weights is dependent on the
        #        activation function used (among other things).
        #        For example, results presented in [Xavier10] suggest that you
        #        should use 4 times larger initial weights for sigmoid
        #        compared to tanh
        #        We have no info for other function, so we use the same as
        #        tanh.
        if W is None:
            W_values = numpy.asarray(
                rng.uniform(
                    low=-numpy.sqrt(6. / (n_in + n_out)),
                    high=numpy.sqrt(6. / (n_in + n_out)),
                    size=(n_in, n_out)
                ),
                dtype=theano.config.floatX
            )
            if activation == theano.tensor.nnet.sigmoid:
                W_values *= 4

            W = theano.shared(value=W_values, name='W', borrow=True)

        if b is None:
            b_values = numpy.zeros((n_out,), dtype=theano.config.floatX)
            b = theano.shared(value=b_values, name='b', borrow=True)

        self.W = W
        self.b = b

注意我们使用了一个给定的非线性函数作为隐藏层的激活函数。默认为tanh，在很多情况下我们会使用其他函数。

        lin_output = T.dot(input, self.W) + self.b
        self.output = (
            lin_output if activation is None
            else activation(lin_output)
        )

如果深入看这个类以图方式执行了计算隐藏层数值 $h(x) = \Phi(x) = s(b^{(1)} + W^{(1)} x)$

如果将这个图作为输入传递到LogisticRegression类，执行此前使用逻辑回归区分MNIST数字教程中的代码，你就可以得到MLP的输出。MLP的执行代码如下：

class MLP(object):
    """Multi-Layer Perceptron Class

    A multilayer perceptron is a feedforward artificial neural network model
    that has one layer or more of hidden units and nonlinear activations.
    Intermediate layers usually have as activation function tanh or the
    sigmoid function (defined here by a ``HiddenLayer`` class)  while the
    top layer is a softmax layer (defined here by a ``LogisticRegression``
    class).
    """

    def __init__(self, rng, input, n_in, n_hidden, n_out):
        """Initialize the parameters for the multilayer perceptron

        :type rng: numpy.random.RandomState
        :param rng: a random number generator used to initialize weights

        :type input: theano.tensor.TensorType
        :param input: symbolic variable that describes the input of the
        architecture (one minibatch)

        :type n_in: int
        :param n_in: number of input units, the dimension of the space in
        which the datapoints lie

        :type n_hidden: int
        :param n_hidden: number of hidden units

        :type n_out: int
        :param n_out: number of output units, the dimension of the space in
        which the labels lie

        """

        # Since we are dealing with a one hidden layer MLP, this will translate
        # into a HiddenLayer with a tanh activation function connected to the
        # LogisticRegression layer; the activation function can be replaced by
        # sigmoid or any other nonlinear function
        self.hiddenLayer = HiddenLayer(
            rng=rng,
            input=input,
            n_in=n_in,
            n_out=n_hidden,
            activation=T.tanh
        )

        # The logistic regression layer gets as input the hidden units
        # of the hidden layer
        self.logRegressionLayer = LogisticRegression(
            input=self.hiddenLayer.output,
            n_in=n_hidden,
            n_out=n_out
        )

这里我们同样使用L1和L2 正则化，这里我们计算W1和W2的L1和平方的L2。

  # L1 norm ; one regularization option is to enforce L1 norm to
        # be small
        self.L1 = (
            abs(self.hiddenLayer.W).sum()
            + abs(self.logRegressionLayer.W).sum()
        )

        # square of L2 norm ; one regularization option is to enforce
        # square of L2 norm to be small
        self.L2_sqr = (
            (self.hiddenLayer.W ** 2).sum()
            + (self.logRegressionLayer.W ** 2).sum()
        )

        # negative log likelihood of the MLP is given by the negative
        # log likelihood of the output of the model, computed in the
        # logistic regression layer
        self.negative_log_likelihood = (
            self.logRegressionLayer.negative_log_likelihood
        )
        # same holds for the function computing the number of errors
        self.errors = self.logRegressionLayer.errors

        # the parameters of the model are the parameters of the two layer it is
        # made out of
        self.params = self.hiddenLayer.params + self.logRegressionLayer.params

如前所述，我们使用随机梯度下降和微批次训练模型。不同的是我们在代价函数中加入了L1_reg和L2_reg超参数来控制正则化在总体损失中的权重。代码如下：

  # the cost we minimize during training is the negative log likelihood of
    # the model plus the regularization terms (L1 and L2); cost is expressed
    # here symbolically
    cost = (
        classifier.negative_log_likelihood(y)
        + L1_reg * classifier.L1
        + L2_reg * classifier.L2_sqr
    )

我们使用梯度更新模型参数时，代码与逻辑回归几乎相同，只是参数量不同。我们使用参数列表params来计算每一步的梯度。

   # compute the gradient of cost with respect to theta (sorted in params)
    # the resulting gradients will be stored in a list gparams
    gparams = [T.grad(cost, param) for param in classifier.params]

    # specify how to update the parameters of the model as a list of
    # (variable, update expression) pairs

    # given two lists of the same length, A = [a1, a2, a3, a4] and
    # B = [b1, b2, b3, b4], zip generates a list C of same size, where each
    # element is a pair formed from the two lists :
    #    C = [(a1, b1), (a2, b2), (a3, b3), (a4, b4)]
    updates = [
        (param, param - learning_rate * gparam)
        for param, gparam in zip(classifier.params, gparams)
    ]

    # compiling a Theano function `train_model` that returns the cost, but
    # in the same time updates the parameter of the model based on the rules
    # defined in `updates`
    train_model = theano.function(
        inputs=[index],
        outputs=cost,
        updates=updates,
        givens={
            x: train_set_x[index * batch_size: (index + 1) * batch_size],
            y: train_set_y[index * batch_size: (index + 1) * batch_size]
        }
    )

MLP代码汇总

如之前所述，我们用于之前逻辑回归相同的方式将所有代码放在一起。

"""
This tutorial introduces the multilayer perceptron using Theano.

 A multilayer perceptron is a logistic regressor where
instead of feeding the input to the logistic regression you insert a
intermediate layer, called the hidden layer, that has a nonlinear
activation function (usually tanh or sigmoid) . One can use many such
hidden layers making the architecture deep. The tutorial will also tackle
the problem of MNIST digit classification.

.. math::

    f(x) = G( b^{(2)} + W^{(2)}( s( b^{(1)} + W^{(1)} x))),

References:

    - textbooks: "Pattern Recognition and Machine Learning" -
                 Christopher M. Bishop, section 5

"""

from __future__ import print_function

__docformat__ = 'restructedtext en'


import os
import sys
import timeit

import numpy

import theano
import theano.tensor as T


from logistic_sgd import LogisticRegression, load_data


# start-snippet-1
class HiddenLayer(object):
    def __init__(self, rng, input, n_in, n_out, W=None, b=None,
                 activation=T.tanh):
        """
        Typical hidden layer of a MLP: units are fully-connected and have
        sigmoidal activation function. Weight matrix W is of shape (n_in,n_out)
        and the bias vector b is of shape (n_out,).

        NOTE : The nonlinearity used here is tanh

        Hidden unit activation is given by: tanh(dot(input,W) + b)

        :type rng: numpy.random.RandomState
        :param rng: a random number generator used to initialize weights

        :type input: theano.tensor.dmatrix
        :param input: a symbolic tensor of shape (n_examples, n_in)

        :type n_in: int
        :param n_in: dimensionality of input

        :type n_out: int
        :param n_out: number of hidden units

        :type activation: theano.Op or function
        :param activation: Non linearity to be applied in the hidden
                           layer
        """
        self.input = input
        # end-snippet-1

        # `W` is initialized with `W_values` which is uniformely sampled
        # from sqrt(-6./(n_in+n_hidden)) and sqrt(6./(n_in+n_hidden))
        # for tanh activation function
        # the output of uniform if converted using asarray to dtype
        # theano.config.floatX so that the code is runable on GPU
        # Note : optimal initialization of weights is dependent on the
        #        activation function used (among other things).
        #        For example, results presented in [Xavier10] suggest that you
        #        should use 4 times larger initial weights for sigmoid
        #        compared to tanh
        #        We have no info for other function, so we use the same as
        #        tanh.
        if W is None:
            W_values = numpy.asarray(
                rng.uniform(
                    low=-numpy.sqrt(6. / (n_in + n_out)),
                    high=numpy.sqrt(6. / (n_in + n_out)),
                    size=(n_in, n_out)
                ),
                dtype=theano.config.floatX
            )
            if activation == theano.tensor.nnet.sigmoid:
                W_values *= 4

            W = theano.shared(value=W_values, name='W', borrow=True)

        if b is None:
            b_values = numpy.zeros((n_out,), dtype=theano.config.floatX)
            b = theano.shared(value=b_values, name='b', borrow=True)

        self.W = W
        self.b = b

        lin_output = T.dot(input, self.W) + self.b
        self.output = (
            lin_output if activation is None
            else activation(lin_output)
        )
        # parameters of the model
        self.params = [self.W, self.b]


# start-snippet-2
class MLP(object):
    """Multi-Layer Perceptron Class

    A multilayer perceptron is a feedforward artificial neural network model
    that has one layer or more of hidden units and nonlinear activations.
    Intermediate layers usually have as activation function tanh or the
    sigmoid function (defined here by a ``HiddenLayer`` class)  while the
    top layer is a softmax layer (defined here by a ``LogisticRegression``
    class).
    """

    def __init__(self, rng, input, n_in, n_hidden, n_out):
        """Initialize the parameters for the multilayer perceptron

        :type rng: numpy.random.RandomState
        :param rng: a random number generator used to initialize weights

        :type input: theano.tensor.TensorType
        :param input: symbolic variable that describes the input of the
        architecture (one minibatch)

        :type n_in: int
        :param n_in: number of input units, the dimension of the space in
        which the datapoints lie

        :type n_hidden: int
        :param n_hidden: number of hidden units

        :type n_out: int
        :param n_out: number of output units, the dimension of the space in
        which the labels lie

        """

        # Since we are dealing with a one hidden layer MLP, this will translate
        # into a HiddenLayer with a tanh activation function connected to the
        # LogisticRegression layer; the activation function can be replaced by
        # sigmoid or any other nonlinear function
        self.hiddenLayer = HiddenLayer(
            rng=rng,
            input=input,
            n_in=n_in,
            n_out=n_hidden,
            activation=T.tanh
        )

        # The logistic regression layer gets as input the hidden units
        # of the hidden layer
        self.logRegressionLayer = LogisticRegression(
            input=self.hiddenLayer.output,
            n_in=n_hidden,
            n_out=n_out
        )
        # end-snippet-2 start-snippet-3
        # L1 norm ; one regularization option is to enforce L1 norm to
        # be small
        self.L1 = (
            abs(self.hiddenLayer.W).sum()
            + abs(self.logRegressionLayer.W).sum()
        )

        # square of L2 norm ; one regularization option is to enforce
        # square of L2 norm to be small
        self.L2_sqr = (
            (self.hiddenLayer.W ** 2).sum()
            + (self.logRegressionLayer.W ** 2).sum()
        )

        # negative log likelihood of the MLP is given by the negative
        # log likelihood of the output of the model, computed in the
        # logistic regression layer
        self.negative_log_likelihood = (
            self.logRegressionLayer.negative_log_likelihood
        )
        # same holds for the function computing the number of errors
        self.errors = self.logRegressionLayer.errors

        # the parameters of the model are the parameters of the two layer it is
        # made out of
        self.params = self.hiddenLayer.params + self.logRegressionLayer.params
        # end-snippet-3

        # keep track of model input
        self.input = input


def test_mlp(learning_rate=0.01, L1_reg=0.00, L2_reg=0.0001, n_epochs=1000,
             dataset='mnist.pkl.gz', batch_size=20, n_hidden=500):
    """
    Demonstrate stochastic gradient descent optimization for a multilayer
    perceptron

    This is demonstrated on MNIST.

    :type learning_rate: float
    :param learning_rate: learning rate used (factor for the stochastic
    gradient

    :type L1_reg: float
    :param L1_reg: L1-norm's weight when added to the cost (see
    regularization)

    :type L2_reg: float
    :param L2_reg: L2-norm's weight when added to the cost (see
    regularization)

    :type n_epochs: int
    :param n_epochs: maximal number of epochs to run the optimizer

    :type dataset: string
    :param dataset: the path of the MNIST dataset file from
                 http://www.iro.umontreal.ca/~lisa/deep/data/mnist/mnist.pkl.gz


   """
    datasets = load_data(dataset)

    train_set_x, train_set_y = datasets[0]
    valid_set_x, valid_set_y = datasets[1]
    test_set_x, test_set_y = datasets[2]

    # compute number of minibatches for training, validation and testing
    n_train_batches = train_set_x.get_value(borrow=True).shape[0] // batch_size
    n_valid_batches = valid_set_x.get_value(borrow=True).shape[0] // batch_size
    n_test_batches = test_set_x.get_value(borrow=True).shape[0] // batch_size

    ######################
    # BUILD ACTUAL MODEL #
    ######################
    print('... building the model')

    # allocate symbolic variables for the data
    index = T.lscalar()  # index to a [mini]batch
    x = T.matrix('x')  # the data is presented as rasterized images
    y = T.ivector('y')  # the labels are presented as 1D vector of
                        # [int] labels

    rng = numpy.random.RandomState(1234)

    # construct the MLP class
    classifier = MLP(
        rng=rng,
        input=x,
        n_in=28 * 28,
        n_hidden=n_hidden,
        n_out=10
    )

    # start-snippet-4
    # the cost we minimize during training is the negative log likelihood of
    # the model plus the regularization terms (L1 and L2); cost is expressed
    # here symbolically
    cost = (
        classifier.negative_log_likelihood(y)
        + L1_reg * classifier.L1
        + L2_reg * classifier.L2_sqr
    )
    # end-snippet-4

    # compiling a Theano function that computes the mistakes that are made
    # by the model on a minibatch
    test_model = theano.function(
        inputs=[index],
        outputs=classifier.errors(y),
        givens={
            x: test_set_x[index * batch_size:(index + 1) * batch_size],
            y: test_set_y[index * batch_size:(index + 1) * batch_size]
        }
    )

    validate_model = theano.function(
        inputs=[index],
        outputs=classifier.errors(y),
        givens={
            x: valid_set_x[index * batch_size:(index + 1) * batch_size],
            y: valid_set_y[index * batch_size:(index + 1) * batch_size]
        }
    )

    # start-snippet-5
    # compute the gradient of cost with respect to theta (sorted in params)
    # the resulting gradients will be stored in a list gparams
    gparams = [T.grad(cost, param) for param in classifier.params]

    # specify how to update the parameters of the model as a list of
    # (variable, update expression) pairs

    # given two lists of the same length, A = [a1, a2, a3, a4] and
    # B = [b1, b2, b3, b4], zip generates a list C of same size, where each
    # element is a pair formed from the two lists :
    #    C = [(a1, b1), (a2, b2), (a3, b3), (a4, b4)]
    updates = [
        (param, param - learning_rate * gparam)
        for param, gparam in zip(classifier.params, gparams)
    ]

    # compiling a Theano function `train_model` that returns the cost, but
    # in the same time updates the parameter of the model based on the rules
    # defined in `updates`
    train_model = theano.function(
        inputs=[index],
        outputs=cost,
        updates=updates,
        givens={
            x: train_set_x[index * batch_size: (index + 1) * batch_size],
            y: train_set_y[index * batch_size: (index + 1) * batch_size]
        }
    )
    # end-snippet-5

    ###############
    # TRAIN MODEL #
    ###############
    print('... training')

    # early-stopping parameters
    patience = 10000  # look as this many examples regardless
    patience_increase = 2  # wait this much longer when a new best is
                           # found
    improvement_threshold = 0.995  # a relative improvement of this much is
                                   # considered significant
    validation_frequency = min(n_train_batches, patience // 2)
                                  # go through this many
                                  # minibatche before checking the network
                                  # on the validation set; in this case we
                                  # check every epoch

    best_validation_loss = numpy.inf
    best_iter = 0
    test_score = 0.
    start_time = timeit.default_timer()

    epoch = 0
    done_looping = False

    while (epoch < n_epochs) and (not done_looping):
        epoch = epoch + 1
        for minibatch_index in range(n_train_batches):

            minibatch_avg_cost = train_model(minibatch_index)
            # iteration number
            iter = (epoch - 1) * n_train_batches + minibatch_index

            if (iter + 1) % validation_frequency == 0:
                # compute zero-one loss on validation set
                validation_losses = [validate_model(i) for i
                                     in range(n_valid_batches)]
                this_validation_loss = numpy.mean(validation_losses)

                print(
                    'epoch %i, minibatch %i/%i, validation error %f %%' %
                    (
                        epoch,
                        minibatch_index + 1,
                        n_train_batches,
                        this_validation_loss * 100.
                    )
                )

                # if we got the best validation score until now
                if this_validation_loss < best_validation_loss:
                    #improve patience if loss improvement is good enough
                    if (
                        this_validation_loss < best_validation_loss *
                        improvement_threshold
                    ):
                        patience = max(patience, iter * patience_increase)

                    best_validation_loss = this_validation_loss
                    best_iter = iter

                    # test it on the test set
                    test_losses = [test_model(i) for i
                                   in range(n_test_batches)]
                    test_score = numpy.mean(test_losses)

                    print(('     epoch %i, minibatch %i/%i, test error of '
                           'best model %f %%') %
                          (epoch, minibatch_index + 1, n_train_batches,
                           test_score * 100.))

            if patience <= iter:
                done_looping = True
                break

    end_time = timeit.default_timer()
    print(('Optimization complete. Best validation score of %f %% '
           'obtained at iteration %i, with test performance %f %%') %
          (best_validation_loss * 100., best_iter + 1, test_score * 100.))
    print(('The code for file ' +
           os.path.split(__file__)[1] +
           ' ran for %.2fm' % ((end_time - start_time) / 60.)), file=sys.stderr)


if __name__ == '__main__':
    test_mlp()

可以通过以下代码运行程序

python code/mlp.py

输出应类似于

Optimization complete. Best validation score of 1.690000 % obtained at iteration 2070000, with test performance 1.650000 %
The code for file mlp.py ran for 97.34m

一些注意事项和技巧

上述代码中有一些超参数没有也无法用梯度下降方式优化。严格讲为这些超参数找到一组最优值并不实际。首先我们无法逐个优化他们，第二我们无法使用之前的梯度方法，因为它们一些是离散数值，一些是连续数值，第三优化问题非弧形，找到最小值十分不易。

好消息是过去25年，研究者设计了一些准则以寻找神经网络中的超参数。详见 Yann LeCun, Leon Bottou, Genevieve Orr, and Klaus-Robert Mueller的http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf

这里我们重点概述一些我们使用的方法

非线性

最常用的是sigmoid和tanh函数。我们希望获得围绕原点对称非线性，因为这样使得下一层的输入平均数为0。实践中观察到tanh有更好的收敛性。

权重初始化

起初我们希望使用围绕原点的小权重，以使得激活函数在线性范围运作，此时梯度最大。其他期望属性，特别是对于深度网络，包括保存层与层之间激活的方差和反向传播梯度方差。这使信息在上下之间流动顺畅，减少层间差异。在一些假设下，tanh采用： $uniform[-\frac{\sqrt{6}}{\sqrt{fan_{in}+fan_{out}}},\frac{\sqrt{6}}{\sqrt{fan_{in}+fan_{out}}}]$