Dataset Groups Activity Stream 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. BibTex: @dataset{Hiroaki_Yamagiwa_and_Momose_Oyama_and_Hidetoshi_Shimodaira_2024, abstract = {This study utilizes Independent Component Analysis (ICA) to unveil a consistent semantic structure within embeddings of words or images.}, author = {Hiroaki Yamagiwa and Momose Oyama and Hidetoshi Shimodaira}, doi = {10.57702/reyklrnj}, institution = {No Organization}, keyword = {'ICA', 'image embeddings', 'semantic structure', 'word embeddings'}, month = {dec}, publisher = {TIB}, title = {Discovering Universal Geometry in Embeddings with ICA}, url = {https://service.tib.eu/ldmservice/dataset/discovering-universal-geometry-in-embeddings-with-ica}, year = {2024} }
