image classification 1model simplification 1neural collapse 1neural network pruning 1training dynamics 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.AI2026
Simplifying Neural Networks During Training
Lorenzo Sciandra, Samuele Fonio, Roberto Esposito
The paper proposes a training framework that monitors representation dynamics using the Inverse Fisher Criterion to identify when and where to replace later layers of a deep networ…
cs.LG2026
Supplementary Materials to Graph Convolutional Branch and Bound
Lorenzo Sciandra, Roberto Esposito, Andrea Cesare Grosso +2
This article explores the integration of deep learning models into combinatorial optimization pipelines, specifically targeting NP-hard problems. Traditional exact algorithms for s…