Publications [#364343] of Vahid Tarokh

Papers Published

1. Soltani, M; Wu, S; Li, Y; Ding, J; Tarokh, V, On The Energy Statistics of Feature Maps in Pruning of Neural Networks with Skip-Connections, Data Compression Conference Proceedings, vol. 2022-March (January, 2022), pp. 482, ISBN 9781665478939 [doi]
   (last updated on 2023/06/01)

   Abstract:
   We propose a new structured pruning framework for compressing Deep Neural Networks (DNNs) with skip-connections, based on measuring the statistical dependency of hidden layers and predicted outputs. The dependence measure defined by the energy statistics of hidden layers serves as a model-free measure of information between the feature maps and the output of the network. The estimated dependence measure is subsequently used to prune a collection of redundant and uninformative layers. Extensive numerical experiments on various architectures show the efficacy of the proposed pruning approach with competitive performance to state-of-the-art methods.