SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance

Dates and versions

hal-03953649 , version 1 (24-01-2023)

Identifiers

Cite

Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly. SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance. Advances in Neural Information Processing Systems (NeurIPS 2022), Nov 2022, New Orleans, United States. ⟨hal-03953649⟩
13 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More