skip to main content

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Friday, December 13 until 2:00 AM ET on Saturday, December 14 due to maintenance. We apologize for the inconvenience.


This content will become publicly available on January 1, 2025

Title: Geometric Graph Filters and Neural Networks: Limit Properties and Discriminability Trade-Offs
Award ID(s):
2031895
PAR ID:
10526703
Author(s) / Creator(s):
; ;
Publisher / Repository:
IEEE Transactions on Signal Processing
Date Published:
Journal Name:
IEEE Transactions on Signal Processing
Volume:
72
ISSN:
1053-587X
Page Range / eLocation ID:
2244 to 2259
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Researchers emphasize the role of math and science identities in science, technology, engineering, and mathematics (STEM) education. However, little is known about whether these identities might evolve during college; likewise it is not known how changes in math and science identities are associated with switching majors between STEM and non-STEM fields. This study addresses these questions. With data from the Pathways through College Study, this study revealed that science identity changes matter more than math identity changes in their association with the decision to switch majors. Most notably, underrepresented racial minority women are the most vulnerable in terms of decreasing science identity and the associated probabilities of leaking out of STEM. The authors also find evidence that Asian students are the least sensitive to their science identity drop. These findings have significant policy implications with regard to STEM choice and attainment.

     
    more » « less