The following snippet shows the usage of Adam with Keras:
from keras.optimizers import Adam
...
adam = Adam(lr=0.0001, beta_1=0.9, beta_2=0.9, epsilon=1e-6, decay=1e-2)
model.compile(optimizer=adam,
loss='categorical_crossentropy',
metrics=['accuracy'])
The forgetting factors, μ1 and μ2, are represented by the parameters beta_1 and beta_2. All the other elements are the same as the other algorithms.