如何添加隐藏层结果？

【问题标题】：how to do addition to hidden layers results?如何添加隐藏层结果？
【发布时间】：2021-05-02 08:54:36
【问题描述】：

假设我们有一个这样的神经网络

input = layers.Input(shape=(num_inputs,))
out = layers.Dense(1028, activation="relu")(input)
out = layers.Dense(512, activation="relu")(out)
out = layers.Dense(256, activation="relu")(out)
output = layers.Dense(4, activation="softmax")(out)

如果我想用随机数添加任何隐藏层结果，代码应该如何更改？？

【问题讨论】：

标签： python tensorflow machine-learning keras neural-network

【解决方案1】：

您可以使用随机数将结果添加到任何隐藏层，如下所示。 Reference and more details.

from tensorflow.keras.layers import *
from tensorflow.keras.models import Model
from tensorflow.keras import backend as K 

ins = Input((1,))

out = Dense(1028, activation="relu")(ins)
out = Lambda(lambda x: K.random_uniform((1,))*x)(out)

out = Dense(512, activation="relu")(out)
out = Lambda(lambda x: K.random_uniform((1,))*x)(out)

out = Dense(256, activation="relu")(out)
out = Lambda(lambda x: K.random_uniform((1,))*x)(out)

outs = Dense(256, activation="softmax")(out)
model = Model(ins, outs)

【讨论】：