Refine
Document Type
- Bachelor Thesis (1) (remove)
Year of publication
- 2018 (1)
Language
- English (1) (remove)
Keywords
- Regularisierung (1) (remove)
Institute
DropConnect (the generalization of Dropout) is a very simple regularization technique that was introduced a few years ago and has become extremely popular because of its simplicity and effectiveness. In this thesis, a suitable architecture for applying DropConnect to Learning Vector Quantization networks is proposed along with a reference implementation and experimental results. Inmany classification tasks, the uncertainty of themodel is a vital piece of information for experts. Methods to extract the uncertainty and stability using DropConnect are also proposed and the corresponding experimental results are documented.