亚当方法学习率高吗？

我正在尝试估计收缩压。我将PPG功能（27）放入了ANN。我得到的结果如下。学习率好吗？如果不是，它是高还是低？这是我的结果。

我将学习率设置为0.000001。我认为它仍然太高。我认为它下降得太快了。

损耗：5.1285-女士：57.7257-val_loss：6.0154-val_mse：73.9671

# import data
data = pandas.read_csv("data.csv",sep=",")
data = data[["cp","st","dt","sw10","dw10","sw10+dw10","dw10/sw10","sw25","dw25","sw25+dw25","dw25/sw25","sw33","dw33","sw33+dw33","dw33/sw33","sw50","dw50","sw50+dw50","dw50/sw50","sw66","dw66","sw66+dw66","dw66/sw66","sw75","dw75","sw75+dw75","dw75/sw75","sys"]]
# data description
described_data = data.describe()
print(described_data)
print(len(data))
# # histograms of input data (features)
# data.hist(figsize=(12,10))
# plt.show()
# index and shuffle data
data.reset_index(inplace=True,drop=True)
data = data.reindex(numpy.random.permutation(data.index))
# x (parameters) and y (blood pressure) data
predict = "sys"
X = numpy.array(data.drop([predict],1))
y = numpy.array(data[predict])
# Splitting the total data into subsets: 90% - training,10% - testing
X_train,X_test,y_train,y_test = sklearn.model_selection.train_test_split(X,y,test_size=0.1,random_state=0)
def feature_normalize(X): # standardization function
mean = numpy.mean(X,axis=0)
std = numpy.std(X,axis=0)
return (X - mean) / std
# Features scaling
X_train_standardized = feature_normalize(X_train)
X_test_standardized = feature_normalize(X_test)
# Build the ANN model
model = Sequential()
# Adding the input layer and the first hidden layer
model.add(Dense(25,activation='sigmoid',input_dim=27))
# Adding the second hidden layer
model.add(Dense(units=15,activation='sigmoid'))
# Adding the output layer
model.add(Dense(units=1,activation='linear',kernel_initializer='normal'))
model.summary()
optimizer = keras.optimizers.Adam(learning_rate=0.000001)
# Compiling the model
model.compile(loss='mae',optimizer='adam',metrics=['mse'])
#Early stopping to prevent overfitting
mOnitor= EarlyStopping(mOnitor='val_loss',min_delta=1e-3,patience=10,verbose=1,mode='auto',restore_best_weights=True)
# Fitting the ANN to the Training set
history = model.fit(X_train_standardized,validation_split=0.2,verbose=2,epochs=1000,batch_size=5)


data
loss

prediction

未使用您的学习率，因为您没有使用Lorem Ipsum simply dummy text -TOKEN_ABC- yes
实例编译模型。

- # a hyphen
[A-Z]+ # 1 or more capitals
(?: # non capture group
_ # underscore
[A-Z]+ # 1 or more capitals
)* # end group,may appear 0 or more times
- # a hyphen
(*SKIP) # forget the match
(*FAIL) # and fail
| # OR
[^\w\s]+ # 1 or more non word characters or spaces


应该是：

optimizer

关于问题本身：正如《混血王子》所说，在不知道您的数据集的情况下很难说。此外，数据本身的状况很重要。我确实会建议以下内容：

• 请考虑将要素放置在（0,1）范围内，这可以通过sklearn.preprocess.MinMaxScaler完成。


• 根据确定的数据优化，而不是用逐步的方法来确定您的超参数，然后在保留测试集上测试最终结果。 Hyper-parameter optimization is so easy with skopt。