In addition to topological data analysis, unsupervised and supervised learning, the project ∂SIML also uses basics of algebraic topology to identify successful schemes. Currently under construction and constantly expanded. A documentation with the description and the corresponding functionality is also created here.
The Machine Learning Library
This repository provides a library for data analysis using clustering algorithms and algorithms for processing functional dependencies in the context of database technologies. The aim is to create a library that enables the development of a prototype for the implementation of automatic or semi-automatic schema inference. When we talk about schema inference, we think of a data stream, or a data set, that initially exists without defined relationtypes. From this, we would like to obtain a suitable schema using clustering techniques in combination with functional dependencies and normalization in order to support the database user.
- Coricos TDAToolbox, https://github.com/Coricos/TdaToolbox.
- Hirosm: Time Contrastive Learning, https://github.com/hirosm/TCL.
- Indoor WIFI Dataset: UJIIndoorLoc, https://archive.ics.uci.edu/ml/datasets/UJIIndoorLoc.
- Nabihach Tane & CTane, https://github.com/nabihach/FD_CFD_extraction.
- P. Fränti and S. Sieranoja: Clustering Basic Benchmarks, http://cs.joensuu.fi/sipu/datasets/.
- PPoffice: Ant-Colony TSP-Solver, https://github.com/ppoffice/ant-colony-tsp.
- Stwisdom: Optimizers, https://github.com/stwisdom/urnn/blob/master/.
- Submanifolds Neural Persistence, https://github.com/BorgwardtLab/Neural-Persistence.