Activation-Based Pruning of Neural Networks

We present a novel technique for pruning called <i>activation-based</i> pruning to effectively prune fully connected feedforward neural networks for multi-object classification. Our technique is based on the number of times each neuron is activated during model training. We compare the p...

Full description

Bibliographic Details
Main Authors: Tushar Ganguli, Edwin K. P. Chong
Format: Article
Language:English
Published: MDPI AG 2024-01-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/17/1/48