BINGO!: A Novel Neural Network Pruning Mechanism to Allow For Physical Computing in AI Education
Name
MIT_AIEDU_2025_paper_170.pdf
Size
824.04 KB
Format
Adobe PDF
Checksum (MD5)
84c255608bbbe09dd663732bb2a02dea
Author(s)
Panangat, Aditya
Date Issued
July 2025
Journal
2025 MIT AI and Education Summit
Abstract
BINGO, during the training pass, studies specific subsets of a neural network one at a time to gauge how significant of a role each weight plays in contributing to a network’s accuracy. By the time training is done, BINGO generates a significance score for each weight, allowing for insignificant weights to be pruned in one shot. BINGO provides an accuracy-preserving pruning technique that is less computationally intensive than current methods, allowing for a world where students can learn about AI through engaging physical computing activities.
Persistent DSpace Link
