D-Score: A Synapse-Inspired Approach for Filter Pruning. (arXiv:2308.04470v1 [cs.NE])

This paper introduces a new aspect for determining the rank of the
unimportant filters for filter pruning on convolutional neural networks (CNNs).
In the human synaptic system, there are two important channels known as
excitatory and inhibitory neurotransmitters that transmit a signal from a
neuron to a cell. Adopting the neuroscientific perspective, we propose a
synapse-inspired filter pruning method, namely Dynamic Score (D-Score). D-Score
analyzes the independent importance of positive and negative weights in the
filters and ranks the independent …

arxiv cnns convolutional neural networks filter filters human networks neural networks neuron paper pruning signal synapse