VQ-VAE with Neural Gas and Fuzzy c-Means
- VQ-VAE is a successful generative model which can perform lossy compression. It combines deep learning with vector quantization to achieve a discrete compressed representation of the data. We explore using different vector quantization techniques with VQ-VAE, mainly neural gas and fuzzy c-means. Moreover, VQ-VAE consists of a non-differentiable discrete mapping which we will explore and propose changes to the original VQ-VAE loss to fit the alternative vector quantization techniques.
Author: | Yahya Badran |
---|---|
Advisor: | Thomas Villmann, Marika Kaden |
Document Type: | Master's Thesis |
Language: | English |
Year of Completion: | 2021 |
Granting Institution: | Hochschule Mittweida |
Release Date: | 2022/03/08 |
GND Keyword: | Vektorquantisierung; Deep learning |
Institutes: | Angewandte Computer‐ und Biowissenschaften |
DDC classes: | 621.3822 digitale Signalverarbeitung, Vektorquantisierung |
Open Access: | Frei zugänglich |
Licence (German): | Urheberrechtlich geschützt |