Hi @wdf19961118
It is a two-stage strategy. If you are familiar with EM (Expectation Maximization Algorithm), the mechanism is somehow similar.
We can not update input and encoder at the same time, which may lead to the optimisation problems such as overfitting.
Hi @wdf19961118 It is a two-stage strategy. If you are familiar with EM (Expectation Maximization Algorithm), the mechanism is somehow similar. We can not update input and encoder at the same time, which may lead to the optimisation problems such as overfitting.