神经网络 – 如何在Keras中添加正交性正则化？

Any function that takes in a weight matrix and returns a loss
contribution tensor can be used as a regularizer

以下是实施的示例：

from keras import backend as K

def l1_reg(weight_matrix):
    return 0.01 * K.sum(K.abs(weight_matrix))

model.add(Dense(64,input_dim=64,kernel_regularizer=l1_reg)

您的帖子中的损失将是：

from keras import backend as K
def fro_norm(w):
    return K.sqrt(K.sum(K.square(K.abs(w))))

def cust_reg(w):
    m = K.dot(K.transpose(w),w) - np.eye(w.shape)
    return fro_norm(m)

这是一个最小的例子：

import numpy as np
from keras import backend as K
from keras.models import Sequential
from keras.layers import Dense,Activation

X = np.random.randn(100,100)
y = np.random.randint(2,size=(100,1))

model = Sequential()

# apply regularization here. applies regularization to the 
# output (activation) of the layer
model.add(Dense(32,input_shape=(100,),activity_regularizer=fro_norm))
model.add(Dense(1))
model.add(Activation('softmax'))

model.compile(loss="binary_crossentropy",optimizer='sgd',metrics=['accuracy'])

model.fit(X,y,epochs=1,batch_size=32)

下面不会像@ Marcin的评论所暗示的那样LA.norm不起作用,因为正规化者必须返回Tensor LA.norm()不会.

def orth_norm(w)
    m = K.dot(k.transpose(w),w) - np.eye(w.shape)
    return LA.norm(m,'fro')

from keras import backend as K

import numpy as np

def orth_norm(w)
    m = K.dot(k.transpose(w),'fro')

Keras regularizers

Frobenias norm