fairfolio
Saved Projects

Towards a Greener AI: Structured Pruning of Convolutional Neural Networks at Initialization

ISEF · 2021 Systems Software Fourth Award

Faux, Sydney · Pace Academy

Is this your project?

Overview

Training deep convolutional neural networks (CNNs) requires immense time and energy, which often has a significant carbon footprint. Pruning CNNs increases their efficiency while maintaining their accuracy. However, pruning is often applied after networks are already trained. Therefore, this paper presents a novel algorithm, FlowPrune, that can prune unimportant filters in CNNs at their initialization. Treating CNNs like flow networks, the Boykov-Kolmogorov maximum flow algorithm is used to find the maximum flow of the network. The filters of the CNN that have the least impact on the "flow" of the model are then pruned to reveal a subnetwork that can achieve similar accuracy as the original network. Experiments on the LeNet-5 and AlexNet CNNs trained on the MNIST and CIFAR-10 datasets demonstrate that this method works and prunes over 60% of the computations necessary to run the CNNs while affecting their accuracy by less than 2% in both cases.

Working on something like this? See what's been done and what's still open.

Awards (3)

  • Fourth Award of $500 $500
  • Association for Computing Machinery: Fourth Award of $500 $500
  • NC State College of Engineering: Award to attend NC State Engineering Summer Camp

Competition history

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Report a problem

Source: Regeneron International Science and Engineering Fair

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google