Loading Now

Summary of Nepenthe: Entropy-based Pruning As a Neural Network Depth’s Reducer, by Zhu Liao et al.


NEPENTHE: Entropy-Based Pruning as a Neural Network Depth’s Reducer

by Zhu Liao, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione

First submitted to arxiv on: 24 Apr 2024

Categories

  • Main: Machine Learning (cs.LG)
  • Secondary: Artificial Intelligence (cs.AI)

     Abstract of paper      PDF of paper


GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty Written by Summary
High Paper authors High Difficulty Summary
Read the original abstract here
Medium GrooveSquid.com (original content) Medium Difficulty Summary
This research proposes a new approach called NEPENTHE to reduce the computational burden of deep neural networks by pruning unimportant connections. The authors identify that many tasks can be solved using shallower models, and their method focuses on removing layers with low entropy to linearize some layers without sacrificing performance. The technique is tested on popular architectures such as MobileNet and Swin-T, showing promise in reducing model depth while maintaining accuracy.
Low GrooveSquid.com (original content) Low Difficulty Summary
Deep neural networks are super smart at solving tricky problems, but they use up a lot of computer power. Researchers have been trying to make these models more efficient by making them smaller, rather than deeper. This new method, called NEPENTHE, helps reduce the size of deep neural networks by removing connections that aren’t very important. The team tested this approach on some popular models and found that it can make the models smaller without losing their ability to solve problems.

Keywords

» Artificial intelligence  » Pruning