# The Simpler The Better: An Entropy-Based Importance Metric To Reduce Neural Networks' Depth Source: [The Simpler The Better: An Entropy-Based Importance Metric To Reduce Neural Networks' Depth]() Collection index: [llms.txt]() Data updated: 2025-10-26T02:50:15.439Z Authors: Victor Qu\\'etu, Zhu Liao, Enzo Tartaglione Published: 2024-04-27T08:28:25.000Z ## Abstract While deep neural networks are highly effective at solving complex tasks, large pre-trained models are commonly employed even to solve consistently simpler downstream tasks, which do not necessarily require a large model's complexity. Motivated by the awareness of the ever-growing AI environmental impact, we propose an efficiency strategy that leverages prior knowledge transferred by large models. Simple but effective, we propose a method relying on an Entropy-bASed Importance mEtRic (EASIER) to reduce the depth of over-parametrized deep neural networks, which alleviates their computational burden. We assess the effectiveness of our method on traditional image classification setups. Our code is available at https://github.com/VGCQ/EASIER. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()