Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published June 15, 2021 | Version v1
Journal article Open

SeReNe: Sensitivity based Regularization of Neurons for Structured Sparsity in Neural Networks

Description

Deep neural networks include millions of learnable parameters, making their deployment over resource-constrained devices problematic. SeReNe (Sensitivity-based Regularization of Neurons) is a method for learning sparse topologies with a structure, exploiting neural sensitivity as a regularizer. We define the sensitivity of a neuron as the variation of the network output with respect to the variation of the activity of the neuron. The lower the sensitivity of a neuron, the less the network output is perturbed if the neuron output changes. By including the neuron sensitivity in the cost function as a regularization term, we are able to prune neurons with low sensitivity. As entire neurons are pruned rather then single parameters, practical network footprint reduction becomes possible. Our experimental results on multiple network architectures and datasets yield competitive compression ratios with respect to state-of-the-art references.

Files

TNNLS21_SeReNe.pdf

Files (766.0 kB)

Name Size Download all
md5:b046c28e6b46677c8d61675f28132ed8
766.0 kB Preview Download

Additional details

Funding

DeepHealth – Deep-Learning and HPC to Boost Biomedical Applications for Health 825111
European Commission