时间戳

首页 > 解决方案 > Keras 中的自定义 Hebbian 层实现 - 输入/输出昏暗和横向节点连接

python - Keras 中的自定义 Hebbian 层实现 - 输入/输出昏暗和横向节点连接

问题描述

我正在尝试在 Keras 中使用 Hebbian 更新来实现无监督的 ANN。我在这里找到了一个由 Dan Saunders 制作的自定义 Hebbian 层 - https://github.com/djsaunde/rinns_python/blob/master/hebbian/hebbian.py （我希望在这里询问关于另一个人的代码的问题并不糟糕）

在我发现在 repo 中使用该层的示例中，该层用作 Dense/Conv 层之间的中间层，但我想仅使用 Hebbian 层构建一个网络。

在这个实现中，有两个关键的事情让我感到困惑：

  1. 似乎输入昏暗和输出昏暗必须相同才能使该层正常工作。为什么会出现这种情况，我该怎么做才能使它们有所不同？

  2. 为什么权重矩阵的对角线设置为零？它说这是为了“确保没有神经元横向连接到自身”，但我认为连接权重在前一层和当前层之间，而不是当前层和自身之间。

这是 Hebbian 层实现的代码：

    from keras import backend as K
    from keras.engine.topology import Layer

    import numpy as np
    import tensorflow as tf

    np.set_printoptions(threshold=np.nan)

    sess = tf.Session()


    class Hebbian(Layer):


    def __init__(self, output_dim, lmbda=1.0, eta=0.0005, connectivity='random', connectivity_prob=0.25, **kwargs):
    '''
    Constructor for the Hebbian learning layer.

    args:
        output_dim - The shape of the output / activations computed by the layer.
        lambda - A floating-point valued parameter governing the strength of the Hebbian learning activation.
        eta - A floating-point valued parameter governing the Hebbian learning rate.
        connectivity - A string which determines the way in which the neurons in this layer are connected to
            the neurons in the previous layer.
    '''
    self.output_dim = output_dim
    self.lmbda = lmbda
    self.eta = eta
    self.connectivity = connectivity
    self.connectivity_prob = connectivity_prob

    if self.connectivity == 'random':
        self.B = np.random.random(self.output_dim) < self.connectivity_prob
    elif self.connectivity == 'zero':
        self.B = np.zeros(self.output_dim)

    super(Hebbian, self).__init__(**kwargs)


    def random_conn_init(self, shape, dtype=None):
    A = np.random.normal(0, 1, shape)
    A[self.B] = 0
    return tf.constant(A, dtype=tf.float32)


    def zero_init(self, shape, dtype=None):
    return np.zeros(shape)


    def build(self, input_shape):
    # create weight variable for this layer according to user-specified initialization
    if self.connectivity == 'all':
        self.kernel = self.add_weight(name='kernel', shape=(np.prod(input_shape[1:]), \
                            np.prod(self.output_dim)), initializer='uniform', trainable=False)
    elif self.connectivity == 'random':
        self.kernel = self.add_weight(name='kernel', shape=(np.prod(input_shape[1:]), \
                            np.prod(self.output_dim)), initializer=self.random_conn_init, trainable=False)
    elif self.connectivity == 'zero':
        self.kernel = self.add_weight(name='kernel', shape=(np.prod(input_shape[1:]), \
                            np.prod(self.output_dim)), initializer=self.zero_init, trainable=False)
    else:
        raise NotImplementedError

    # ensure that no neuron is laterally connected to itself
    self.kernel = self.kernel * tf.diag(tf.zeros(self.output_dim))

    # call superclass "build" function
    super(Hebbian, self).build(input_shape)


    def call(self, x):
    x_shape = tf.shape(x)
    batch_size = tf.shape(x)[0]

    # reshape to (batch_size, product of other dimensions) shape
    x = tf.reshape(x, (tf.reduce_prod(x_shape[1:]), batch_size))

    # compute activations using Hebbian-like update rule
    activations = x + self.lmbda * tf.matmul(self.kernel, x)

    # compute outer product of activations matrix with itself
    outer_product = tf.matmul(tf.expand_dims(x, 1), tf.expand_dims(x, 0))

    # update the weight matrix of this layer
    self.kernel = self.kernel + tf.multiply(self.eta, tf.reduce_mean(outer_product, axis=2))
    self.kernel = tf.multiply(self.kernel, self.B)
    self.kernel = self.kernel * tf.diag(tf.zeros(self.output_dim))

    return K.reshape(activations, x_shape)

在第一次检查时，我希望该层能够从前一层获取输入，执行简单的激活计算（输入 * 权重），根据 Hebbian 更新更新权重（类似于 - 如果激活是高 b/t 节点，则增加权重），然后将激活传递到下一层。

我还希望它能够处理从一层到下一层减少/增加节点数量的问题。

相反，我似乎无法弄清楚为什么输入和输出暗淡必须相同以及为什么权重矩阵的对角线设置为零。

代码中的哪里（隐式或显式）是层需要相同暗度的规范？

代码中的什么地方（隐式或显式）是该层的权重矩阵将当前层连接到自身的规范？

抱歉，如果这个 Q 应该被分成 2，但似乎它们可能与 e/o 有关，所以我将它们保留为 1。

如果需要，很高兴提供更多详细信息。

编辑：意识到我忘记添加当我尝试创建具有与输入暗淡不同的输出暗淡的图层时收到的错误消息：

model = Sequential()
model.add(Hebbian(input_shape = (256,1), output_dim = 256))

这编译没有错误^

model = Sequential()
model.add(Hebbian(input_shape = (256,1), output_dim = 24))

此 ^ 引发错误：IndexError: boolean index did not match indexed array along dimension 0; 维度是 256 但对应的布尔维度是 24

标签： pythontensorflowkerasneural-networkunsupervised-learning

解决方案

好吧，我想我可能想通了，有点。有很多小问题，但最大的问题是我需要添加 compute_output_shape 函数，它使层能够修改其输入的形状，如下所述： https ://keras.io/layers/writing-your-own-keras -层/

所以这是我所做的所有更改的代码。它将编译和修改输入形状就好了。请注意，该层计算层本身内部的权重变化，如果您尝试实际使用该层，可能会出现一些问题（我仍在解决这些问题），但这是一个单独的问题。

class Hebbian(Layer):


def __init__(self, output_dim, lmbda=1.0, eta=0.0005, connectivity='random', connectivity_prob=0.25, **kwargs):
    '''
    Constructor for the Hebbian learning layer.

    args:
        output_dim - The shape of the output / activations computed by the layer.
        lambda - A floating-point valued parameter governing the strength of the Hebbian learning activation.
        eta - A floating-point valued parameter governing the Hebbian learning rate.
        connectivity - A string which determines the way in which the neurons in this layer are connected to
            the neurons in the previous layer.
    '''
    self.output_dim = output_dim
    self.lmbda = lmbda
    self.eta = eta
    self.connectivity = connectivity
    self.connectivity_prob = connectivity_prob

    super(Hebbian, self).__init__(**kwargs)



def random_conn_init(self, shape, dtype=None):
    A = np.random.normal(0, 1, shape)
    A[self.B] = 0
    return tf.constant(A, dtype=tf.float32)


def zero_init(self, shape, dtype=None):
    return np.zeros(shape)


def build(self, input_shape):
    # create weight variable for this layer according to user-specified initialization
    if self.connectivity == 'random':
        self.B = np.random.random(input_shape[0]) < self.connectivity_prob
    elif self.connectivity == 'zero':
        self.B = np.zeros(self.output_dim)

    if self.connectivity == 'all':
        self.kernel = self.add_weight(name='kernel', shape=(np.prod(input_shape[1:]), \
                    np.prod(self.output_dim)), initializer='uniform', trainable=False)
    elif self.connectivity == 'random':
        self.kernel = self.add_weight(name='kernel', shape=(np.prod(input_shape[1:]), \
                    np.prod(self.output_dim)), initializer=self.random_conn_init, trainable=False)
    elif self.connectivity == 'zero':
        self.kernel = self.add_weight(name='kernel', shape=(np.prod(input_shape[1:]), \
                    np.prod(self.output_dim)), initializer=self.zero_init, trainable=False)
    else:
        raise NotImplementedError


    # call superclass "build" function
    super(Hebbian, self).build(input_shape)


def call(self, x):  # x is the input to the network
    x_shape = tf.shape(x)
    batch_size = tf.shape(x)[0]

    # reshape to (batch_size, product of other dimensions) shape
    x = tf.reshape(x, (tf.reduce_prod(x_shape[1:]), batch_size))

    # compute activations using Hebbian-like update rule
    activations = x + self.lmbda * tf.matmul(self.kernel, x)  


    # compute outer product of activations matrix with itself
    outer_product = tf.matmul(tf.expand_dims(x, 1), tf.expand_dims(x, 0)) 

    # update the weight matrix of this layer
    self.kernel = self.kernel + tf.multiply(self.eta, tf.reduce_mean(outer_product, axis=2)) 
    self.kernel = tf.multiply(self.kernel, self.B)
    return K.reshape(activations, x_shape)

def compute_output_shape(self, input_shape):
    return (input_shape[0], self.output_dim)

推荐阅读