Avoiding Retraining in a Simple Direct Transmission Network

Question

Using the pima diabetes diabetes dataset I am trying to build an accurate model using Keras. I wrote the following code:

# Visualize training history
from keras import callbacks
from keras.layers import Dropout

tb = callbacks.TensorBoard(log_dir='/.logs', histogram_freq=10, batch_size=32,
                           write_graph=True, write_grads=True, write_images=False,
                           embeddings_freq=0, embeddings_layer_names=None, embeddings_metadata=None)
# Visualize training history
from keras.models import Sequential
from keras.layers import Dense
import matplotlib.pyplot as plt
import numpy

# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# load pima indians dataset
dataset = numpy.loadtxt("pima-indians-diabetes.csv", delimiter=",")
# split into input (X) and output (Y) variables
X = dataset[:, 0:8]
Y = dataset[:, 8]
# create model
model = Sequential()
model.add(Dense(12, input_dim=8, kernel_initializer='uniform', activation='relu', name='first_input'))
model.add(Dense(500, activation='tanh', name='first_hidden'))
model.add(Dropout(0.5, name='dropout_1'))
model.add(Dense(8, activation='relu', name='second_hidden'))
model.add(Dense(1, activation='sigmoid', name='output_layer'))

# Compile model
model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

# Fit the model
history = model.fit(X, Y, validation_split=0.33, epochs=1000, batch_size=10, verbose=0, callbacks=[tb])
# list all data in history
print(history.history.keys())
# summarize history for accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()

After several attempts, I added dropout levels to avoid overriding, but no luck. The following graph shows that test losses and learning losses become separate at one point.

What else can I do to optimize this network?

UPDATE: based on the comments I received, I changed the code like this:

model = Sequential()
model.add(Dense(12, input_dim=8, kernel_initializer='uniform', kernel_regularizer=regularizers.l2(0.01),
                activity_regularizer=regularizers.l1(0.01), activation='relu',
                name='first_input'))  # added regularizers
model.add(Dense(8, activation='relu', name='first_hidden'))  # reduced to 8 neurons
model.add(Dropout(0.5, name='dropout_1'))
model.add(Dense(5, activation='relu', name='second_hidden'))
model.add(Dense(1, activation='sigmoid', name='output_layer'))

Here are the graphs for 500 eras

Answer 1

> 75%, < 65%, 100, 0,5 , → 0,6. ?

- under-fitting: . over-fitting, overfitting (early stopping). ​​ 100 , , .

, , , .

, over-fitting ? early stopping.

: early stopping input scaling.

 # input scaling
 scaler = StandardScaler()
 X = scaler.fit_transform(X)

 # Early stopping  
 early_stop = EarlyStopping(monitor='val_loss', min_delta=0, patience=3, verbose=1, mode='auto')

 # create model - almost the same code
 model = Sequential()
 model.add(Dense(12, input_dim=8, activation='relu', name='first_input'))
 model.add(Dense(500, activation='relu', name='first_hidden'))
 model.add(Dropout(0.5, name='dropout_1'))
 model.add(Dense(8, activation='relu', name='second_hidden'))
 model.add(Dense(1, activation='sigmoid', name='output_layer')))

 history = model.fit(X, Y, validation_split=0.33, epochs=1000, batch_size=10, verbose=0, callbacks=[tb, early_stop])

Accuracy loss:

Answer 2

(https://keras.io/regularizers/), :

model.add(Dense(12, input_dim=12,
            kernel_regularizer=regularizers.l2(0.01),
            activity_regularizer=regularizers.l1(0.01)))

, , , 500 - , , , , . , relu. , 0,75 ( ). , , - .

Answer 3

For a data set such as diabetes, you can use a much simpler network. Try to reduce the neurons in the second layer. (Is there a specific reason why you chose tanh as the activation there?).

Alternatively, you can simply add an EarlyStopping callback to your training: https://keras.io/callbacks/