| Autor: |
Rey, Luis A. Pérez, Tonnaer, Loek, Menkovski, Vlado, Holenderski, Mike, Portegies, Jacobus W. |
| Rok vydání: |
2020 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
The definition of Linear Symmetry-Based Disentanglement (LSBD) proposed by (Higgins et al., 2018) outlines the properties that should characterize a disentangled representation that captures the symmetries of data. However, it is not clear how to measure the degree to which a data representation fulfills these properties. We propose a metric for the evaluation of the level of LSBD that a data representation achieves. We provide a practical method to evaluate this metric and use it to evaluate the disentanglement of the data representations obtained for three datasets with underlying $SO(2)$ symmetries. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
