Saved in:
Bibliographic Details
Main Authors: Brenner, Rorry, Davis, Evan, Chaudhari, Rushi, Morse, Rowan, Chen, Jingyao, Liu, Xirui, You, Zhaoyi, Itti, Laurent
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.00356
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916770452865024
author Brenner, Rorry
Davis, Evan
Chaudhari, Rushi
Morse, Rowan
Chen, Jingyao
Liu, Xirui
You, Zhaoyi
Itti, Laurent
author_facet Brenner, Rorry
Davis, Evan
Chaudhari, Rushi
Morse, Rowan
Chen, Jingyao
Liu, Xirui
You, Zhaoyi
Itti, Laurent
contents Perforated Backpropagation is a neural network optimization technique based on modern understanding of the computational importance of dendrites within biological neurons. This paper explores further experiments from the original publication, generated from a hackathon held at the Carnegie Mellon Swartz Center in February 2025. Students and local Pittsburgh ML practitioners were brought together to experiment with the Perforated Backpropagation algorithm on the datasets and models which they were using for their projects. Results showed that the system could enhance their projects, with up to 90% model compression without negative impact on accuracy, or up to 16% increased accuracy of their original models.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00356
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring the Performance of Perforated Backpropagation through Further Experiments
Brenner, Rorry
Davis, Evan
Chaudhari, Rushi
Morse, Rowan
Chen, Jingyao
Liu, Xirui
You, Zhaoyi
Itti, Laurent
Machine Learning
Artificial Intelligence
Perforated Backpropagation is a neural network optimization technique based on modern understanding of the computational importance of dendrites within biological neurons. This paper explores further experiments from the original publication, generated from a hackathon held at the Carnegie Mellon Swartz Center in February 2025. Students and local Pittsburgh ML practitioners were brought together to experiment with the Perforated Backpropagation algorithm on the datasets and models which they were using for their projects. Results showed that the system could enhance their projects, with up to 90% model compression without negative impact on accuracy, or up to 16% increased accuracy of their original models.
title Exploring the Performance of Perforated Backpropagation through Further Experiments
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.00356