A logifold structure on measure space
This work addresses data classification problems for researchers and practitioners, but appears incremental as it builds on existing network models and mathematical foundations.
The paper tackles the problem of understanding datasets by developing a local-to-global, measure-theoretical approach using network models as local charts, and shows in experiments that this method can find fuzzy domains and improve accuracy in data classification problems.
In this paper,we develop a local-to-global and measure-theoretical approach to understand datasets. The idea is to take network models with restricted domains as local charts of datasets. We develop the mathematical foundations for these structures, and show in experiments how it can be used to find fuzzy domains and to improve accuracy in data classification problems.