So basically there are 2 issues with data production: intra-cluster sparsity (providing too few…

Original article can be found here (source): Artificial Intelligence on Medium

If the space has discontinuities (eg. gaps between clusters) and you sample/generate a variation from there, the decoder will simply generate an unrealistic output, because the decoder has no idea how to deal with that region of the latent space. During training, it never saw encoded vectors coming from that region of latent space.