AI RESEARCH
Investigating the Effect of Network Pruning on Performance and Interpretability
arXiv CS.LG
•
ArXi:2409.19727v3 Announce Type: replace 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 connection sparsity (pruning of input weights) methods to the network and analyze the outcomes regarding the network's performance on the validation set of ImageNet. We also compare different re.