Year: 2020
Type: preprint
Abstract: We study random embeddings produced by untrained neural set functions, and show that they are powerful representations which well capture the input features for downstream tasks such as classification, and are often linearly separable. We obtain surprising results that show that random set functions can often obtain close to or even better accuracy than fully trained models. We investigate factors that affect the representative power of such embeddings quantitatively and qualitatively.
Source: arXiv (Cornell University)
Authors: Sanghi, Aditya, Jayaraman, Pradeep Kumar
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3010786176