Activation function impact on Sparse Neural Networks
arXiv:2010.05943
Abstract
While the concept of a Sparse Neural Network has been researched for some time, researchers have only recently made notable progress in the matter. Techniques like Sparse Evolutionary Training allow for significantly lower computational complexity when compared to fully connected models by reducing redundant connections. That typically takes place in an iterative process of weight creation and removal during network training. Although there have been numerous approaches to optimize the redistribution of the removed weights, there seems to be little or no study on the effect of activation functions on the performance of the Sparse Networks. This research provides insights into the relationship between the activation function used and the network performance at various sparsity levels.
References in corpus (9)
- Activation Functions: Comparison of trends in Practice and Research for Deep Learning
- Searching for Activation Functions
- Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science
- All you need is a good init
- Sparse Networks from Scratch: Faster Training without Losing Performance
- Deep Rewiring: Training very sparse deep networks
- Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization
- Rigging the Lottery: Making All Tickets Winners
- Deep Learning with S-shaped Rectified Linear Activation Units