Skip to main content
. 2019 Aug 3;21(8):758. doi: 10.3390/e21080758

Figure 5.

Figure 5

MNIST test reconstruction with a VAE; training on varying dataset sizes, architectures, and model capacities. (a) Varying the number of samples. Depending on the size of the dataset, higher capacities of the model are required to fit all the data points; (b) Varying architecture. Overfitting is not getting worse for more layers if the capacity is low enough. More layers do overfit only for higher capacities.