可训练的多参数激活。功能(RBF)NeuPy / Theano

时间:2018-04-18 20:33:58

标签: python machine-learning theano neupy

如何在Neupy或Theano中实现自定义激活功能(通过梯度下降调整均值和方差的RBF内核)以用于Neupy。

{快速背景:渐变下降适用于网络中的每个参数。我想创建一个专门的功能空间,其中包含优化的功能参数,因此Neupy}

我认为我的问题在于参数的创建,尺寸的大小以及它们的连接方式。

感兴趣的主要功能。

激活功能类

class RBF(layers.ActivationLayer):
    def initialize(self):
        super(RBF, self).initialize()
        self.add_parameter(name='mean', shape=(1,),
                       value=init.Normal(), trainable=True)
        self.add_parameter(name='std_dev', shape=(1,),
                       value=init.Normal(), trainable=True)
    def output(self, input_value):
        return rbf(input_value, self.parameters)

RBF功能

def rbf(input_value, parameters):
    K = _outer_substract(input_value, parameters['mean'])
    return np.exp(- np.linalg.norm(K)/parameters['std_dev'])

塑造函数?

def _outer_substract(x, y):
    return (x - y.T).T

将非常感谢帮助,因为这将提供有关如何自定义neupy网络的深刻见解。文档可以在某些领域使用一些工作来说至少......

2 个答案:

答案 0 :(得分:1)

当图层更改输入变量的形状时,它必须通知后续图层有关更改的信息。对于这种情况,它必须具有自定义的output_shape属性。例如:

from neupy import layers
from neupy.utils import as_tuple
import theano.tensor as T

class Flatten(layers.BaseLayer):
    """
    Slight modification of the Reshape layer from the neupy library:
    https://github.com/itdxer/neupy/blob/master/neupy/layers/reshape.py
    """
    @property 
    def output_shape(self):
        # Number of output feature depends on the input shape 
        # When layer receives input with shape (10, 3, 4)
        # than output will be (10, 12). First number 10 defines
        # number of samples which you typically don't need to
        # change during propagation
        n_output_features = np.prod(self.input_shape)
        return (n_output_features,)

    def output(self, input_value):
        n_samples = input_value.shape[0]
        return T.reshape(input_value, as_tuple(n_samples, self.output_shape))

如果你在终端中运行它,你会发现它有效

>>> network = layers.Input((3, 4)) > Flatten()
>>> predict = network.compile()
>>> predict(np.random.random((10, 3, 4))).shape
(10, 12)

在您的示例中,我可以看到一些问题:

  1. rbf函数不会返回theano表达式。在函数编译期间它应该失败
  2. 如果您未指定想要计算范数的轴,则np.linalg.norm等函数将返回标量。
  3. 以下解决方案适合您

    import numpy as np
    from neupy import layers, init
    import theano.tensor as T
    
    
    def norm(value, axis=None):
        return T.sqrt(T.sum(T.square(value), axis=axis))
    
    
    class RBF(layers.BaseLayer):
        def initialize(self):
            super(RBF, self).initialize()
    
            # It's more flexible when shape of the parameters
            # denend on the input shape
            self.add_parameter(
                name='mean', shape=self.input_shape,
                value=init.Constant(0.), trainable=True)
    
            self.add_parameter(
                name='std_dev', shape=self.input_shape,
                value=init.Constant(1.), trainable=True)
    
        def output(self, input_value):
            K = input_value - self.mean
            return T.exp(-norm(K, axis=0) / self.std_dev)
    
    
    network = layers.Input(1) > RBF()
    predict = network.compile()
    print(predict(np.random.random((10, 1))))
    
    network = layers.Input(4) > RBF()
    predict = network.compile()
    print(predict(np.random.random((10, 4))))
    

答案 1 :(得分:0)

虽然itdxer充分回答了这个问题,但我想为这个问题添加确切的解决方案。

架构的创建

network = layers.Input(size) > RBF() > layers.Softmax(num_out)

激活功能

    # Elementwise Gaussian (RBF)
    def rbf(value, mean, std):
        return T.exp(-.5*T.sqr(value-mean)/T.sqr(std))/(std*T.sqrt(2*np.pi))

RBF等级

    class RBF(layers.BaseLayer):

        def initialize(self):

            # Begin by initializing.
            super(RBF, self).initialize()

            # Add parameters to train
            self.add_parameter(name='means', shape=self.input_shape,
                           value=init.Normal(), trainable=True)
            self.add_parameter(name='std_dev', shape=self.input_shape,
                           value=init.Normal(), trainable=True)

        # Define output function for the RBF layer.
        def output(self, input_value):
            K = input_value - self.means
            return rbf(input_value,self.means,self.std_dev

培训

如果您对培训感兴趣。它很简单,

# Set training algorithm
gdnet = algorithms.Momentum(
    network,
    momenutm = 0.1
)

# Train. 
gdnet.train(x,y,max_iter=100)

使用正确的输入和目标进行编译,并在元素方面更新均值和方差。