我正在尝试使用Keras中的Hebbian更新来实现无监督的ANN。我在这里找到了由丹·桑德斯(Dan Saunders)制作的自定义Hebbian图层-https://github.com/djsaunde/rinns_python/blob/master/hebbian/hebbian.py
(我希望在这里问有关他人代码的问题的形式不是很差)

在我在回购中使用此层的示例中,该层用作Dense / Conv层之间的中间层,但是我想仅使用Hebbian层构建网络。

在此实现过程中,有两个关键问题使我感到困惑:


好像输入暗淡和输出暗淡必须相同才能使此层起作用。为什么会这样,我该怎么做才能使它们有所不同?
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其自身”,但是我认为连接权重在上一层和当前层之间,而不是在当前层和其本身之间。


以下是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)


在初次检查时,我希望该层能够从上一层获取输入,执行简单的激活计算(输入*权重),根据Hebbian更新来更新权重(例如-如果激活是高b / t节点,则增加重量),然后将激活信息传递到下一层。

我还期望它能够处理从一层到另一层的节点数量的减少/增加。

取而代之的是,我似乎无法弄清楚为什么输入和输出的暗点必须相同,以及为什么权重矩阵的对角线设置为零。

在代码中的位置(隐式或显式)在哪里规定层必须是相同的暗淡?

在代码中(隐式或显式)在哪里指定该层的权重矩阵将当前层与其自身相连?

抱歉,如果将此Q分隔为2,但似乎它们可能与e / o有关,因此我将其保留为1。

如有需要,乐意提供更多详细信息。

编辑:意识到我忘了添加尝试创建输出暗淡与输入暗淡不同的图层时得到的错误消息:

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


这编译时没有错误^

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


此^引发错误:
IndexError:布尔索引与维度0上的索引数组不匹配;维度为256,但相应的布尔维度为24

最佳答案

好吧,我想我可能知道了。有很多小问题,但是最大的问题是我需要添加compute_output_shape函数,该函数使该层能够修改其输入的形状,如下所述:
https://keras.io/layers/writing-your-own-keras-layers/

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,则可能会有一些问题(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)

07-24 09:53