Stacked Autoencoder

Question

I have a basic autoencoder structure. I want to change it to a stacked autoencoder. From what I know the stacked AE differs in 2 ways:

1. It is made up of layers of sparse vanilla AEs
2. It does layer-wise training.

I want to know if sparsity is a necessity for stacked AEs or just increasing number of hidden layers in vanilla AE structure will make it a stacked AE?

class Autoencoder(Chain):
  def __init__(self):
    super().__init__()
    with self.init_scope():
  # encoder part
      self.l1 = L.Linear(1308608,500)
      self.l2 = L.Linear(500,100)
  # decoder part
      self.l3 = L.Linear(100,500)
      self.l4 = L.Linear(500,1308608)

  def forward(self,x):
      h = self.encode(x)
      x_recon = self.decode(h)
      return x_recon

  def __call__(self,x):
      x_recon = self.forward(x)
      loss = F.mean_squared_error(h, x)
      return loss

  def encode(self, x, train=True):
      h = F.dropout(self.activation(self.l1(x)), train=train)
      return self.activation(self.l2(x))

  def decode(self, h, train=True):
      h = self.activation(self.l3(h))
      return self.l4(x)

Answer 1

It seems to be the case that sparsity if often mention in the context of stacked autoencoder, but not necessarily. Hence, I don't think that it is necessary.