用于回归的 LSTM

LSTM used for regression

问题:我有 ST 时间步的序列,每个时间步都包含 F 特征如此集中,一个数据集 (S x T x F) 并且 S 中的每个 s 由 2 个值描述 (Target_1Target_2)

目标:Model/Train 使用 LSTM 的架构,以便 learn/achieve 函数逼近模型 M 并给定序列 s,预测 Target_1Target_2 ?

像这样:

M(s)~(Target_1,Target_2)

我真的很难找到一种方法,下面是一个可能不起作用的示例的 Keras 实现。我制作了 2 个模型,一个用于第一个目标值,一个用于第二个。

model1 = Sequential()
model1.add(Masking(mask_value=-10.0))
model1.add(LSTM(1, input_shape=(batch, timesteps, features), return_sequences = True))  
model1.add(Flatten())
model1.add(Dense(hidden_units, activation = "relu"))
model1.add(Dense(1, activation = "linear"))
model1.compile(loss='mse', optimizer=Adam(learning_rate=0.0001))
model1.fit(x_train, y_train[:,0], validation_data=(x_test, y_test[:,0]), epochs=epochs, batch_size=batch, shuffle=False)

model2 = Sequential()
model2.add(Masking(mask_value=-10.0))
model2.add(LSTM(1, input_shape=(batch, timesteps, features), return_sequences=True))
model2.add(Flatten())
model2.add(Dense(hidden_units, activation = "relu"))
model2.add(Dense(1, activation = "linear"))
model2.compile(loss='mse', optimizer=Adam(learning_rate=0.0001))
model2.fit(x_train, y_train[:,1], validation_data=(x_test, y_test[:,1]), epochs=epochs, batch_size=batch, shuffle=False)

我想以某种方式很好地利用 LSTM 的时间相关记忆,以实现良好的回归。

IIUC,您可以从使用两个输出层的简单(幼稚)方法开始:

import tensorflow as tf

timesteps, features = 20, 5
inputs = tf.keras.layers.Input((timesteps, features))
x = tf.keras.layers.Masking(mask_value=-10.0)(inputs)
x = tf.keras.layers.LSTM(32, return_sequences=False)(x)
x = tf.keras.layers.Dense(32, activation = "relu")(x)
output1 = Dense(1, activation = "linear", name='output1')(x)
output2 = Dense(1, activation = "linear", name='output2')(x)

model = tf.keras.Model(inputs, [output1, output2])
model.compile(loss='mse', optimizer=tf.keras.optimizers.Adam(learning_rate=0.0001))

x_train = tf.random.normal((500, timesteps, features))
y_train = tf.random.normal((500, 2))
model.fit(x_train, [y_train[:,0],y_train[:,1]] , epochs=5, batch_size=32, shuffle=False)