.png){kind=icon}
.png){kind=icon}
Return
LOss-Based SensiTivity rEgulaRization: Towards deep sparse neural networks
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2021.11.029.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
LOBSTER (LOss-Based SensiTivity rEgulaRization) is a method for training neural networks having a sparse topology. Let the sensitivity of a network parameter be the variation of the loss function with respect to the variation of the parameter. Parameters with low sensitivity, i.e. having little impact on the loss when perturbed, are shrunk and then pruned to sparsify the network. Our method allows to train a network from scratch, i.e. without preliminary learning or rewinding. Experiments on multiple architectures and datasets show competitive compression ratios with minimal computational overhead. (C) 2021 Elsevier Ltd. All rights reserved.
Keywords:
Pruning
Regularization
Deep learning
Sparsity
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.