20
0

Exploring the Performance of Perforated Backpropagation through Further Experiments

Main:10 Pages
7 Figures
1 Tables
Abstract

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.

View on arXiv
@article{brenner2025_2506.00356,
  title={ Exploring the Performance of Perforated Backpropagation through Further Experiments },
  author={ Rorry Brenner and Evan Davis and Rushi Chaudhari and Rowan Morse and Jingyao Chen and Xirui Liu and Zhaoyi You and Laurent Itti },
  journal={arXiv preprint arXiv:2506.00356},
  year={ 2025 }
}
Comments on this paper