We present a new method for structured pruning of neural networks, based on the recently proposed neuron merging trick in which following a pruning operation, the weights of the next layer are suitably modified. By a rigorous mathematical analysis of the neuron merging technique we prove an upper bound on the reconstruction error. This bound defines a new objective function for pruning-and-merging.
Articles
Related Articles
April 13, 2023
accelerating wrf i/o performance with adios2 and network-based streaming
With the approach of Exascale computing power for large-scale High Performance Computing (HPC) clusters, the gap...
Read More >
1 MIN READING
February 8, 2021
A Study on MIMO Channel Estimation by 2D and 3D Convolutional Neural Networks
In this paper we study the usage of Convolutional Neural Network (CNN) estimators for the task...
Read More >
1 MIN READING
March 5, 2023
Statistical Properties of NLIN in Presence of PDL
We present an analytical model which predicts the statistical properties of nonlinear interference noise in fiber...
Read More >
1 MIN READING