Poster, Activation function impact on Sparse Neural Networks

Activation function impact on Sparse Neural Networks

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.

  • CS & BIT: Research Project

    The Research Project is a research project that serves as an exercise for the master’s thesis. As such it serves to give master students who did their bachelor study elsewhere the experience that bachelor students from the UT obtained during their bachelor project.

  • Research Paper

    View the full research paper for this project.

Poster, Activation function impact on Sparse Neural Networks

Activation function impact on Sparse Neural Networks

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.

Adam Dubowski

CS & BIT: Research Project

The Research Project is a research project that serves as an exercise for the master’s thesis. As such it serves to give master students who did their bachelor study elsewhere the experience that bachelor students from the UT obtained during their bachelor project.

Research Paper

View the full research paper for this project.