Add Multilayer Perceptron (MLP) primitive for binary classification

[Hector-hedb12]

Related to #121

[Hector-hedb12]

I would like to work on this

[csala]

@Hector-hedb12 Would you mind adding here the link to the corresponding section in the keras docs and summarize what the architecture will be?

Just to keep track of what each issue is

[Hector-hedb12]

The architecture would be:

Dense (ReLU) layer ---> Dropout layer --> Dense (ReLU) layer ---> Dropout layer --> Dense (sigmoid) layer

You can find an example of this here in the MLP for binary classification section:

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout

# Generate dummy data
x_train = np.random.random((1000, 20))
y_train = np.random.randint(2, size=(1000, 1))
x_test = np.random.random((100, 20))
y_test = np.random.randint(2, size=(100, 1))

model = Sequential()
model.add(Dense(64, input_dim=20, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))

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

model.fit(x_train, y_train,
          epochs=20,
          batch_size=128)
score = model.evaluate(x_test, y_test, batch_size=128)