=================================================================================

Adam optimization algorithm is a stochastic gradient descent method that is based on adaptive estimation of first-order and second-order moments. This algorithm helps in compiling the Keras model by updating network weights iteratively based on training data and by diagonal rescaling of the gradients.

Adam class:
          tf.keras.optimizers.Adam(
          learning_rate=0.001,
          beta_1=0.9,
          beta_2=0.999,
          epsilon=1e-07,
          amsgrad=False,
          name="Adam",
          **kwargs
          )

============================================