Autoencoding topology
arXiv:1803.00156v114 citations
Originality Synthesis-oriented
AI Analysis
This addresses the challenge of manifold learning for datasets, though it appears incremental as it builds on existing autoencoder methods.
The paper tackles the problem of learning a manifold structure on a dataset by framing it as a generative model using autoencoder ideas, resulting in an atlas that combines dimensionality reduction and fuzzy clustering.
The problem of learning a manifold structure on a dataset is framed in terms of a generative model, to which we use ideas behind autoencoders (namely adversarial/Wasserstein autoencoders) to fit deep neural networks. From a machine learning perspective, the resulting structure, an atlas of a manifold, may be viewed as a combination of dimensionality reduction and "fuzzy" clustering.