Investigating the Effect of Network Pruning on Performance and Interpretability 事件

Investigating the Effect of Network Pruning on Performance and Interpretability arXiv:2409.19727v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) are often over-parameterized for their tasks and can be compressed quite drastically by removing weights, a process called pruning. We investigate the impact of different pruning techniques on the classification performance and interpretability of GoogLeNet. We systematically apply unstructured and structured pruning, as well as co