Discovering Universal Geometry in Embeddings with ICA

This study utilizes Independent Component Analysis (ICA) to unveil a consistent semantic structure within embeddings of words or images.

Data and Resources

Cite this as

Hiroaki Yamagiwa, Momose Oyama, Hidetoshi Shimodaira (2024). Dataset: Discovering Universal Geometry in Embeddings with ICA. https://doi.org/10.57702/reyklrnj

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2305.13175
Author Hiroaki Yamagiwa
More Authors
Momose Oyama
Hidetoshi Shimodaira
Homepage https://github.com/shimo-lab/Universal-Geometry-with-ICA