AAAI 2023technical0 citations
Backforward Propagation (Student Abstract)
George Stoica, Cristian Simionescu
Abstract
In this paper we introduce Backforward Propagation, a method of completely eliminating Internal Covariate Shift (ICS). Unlike previous methods, which only indirectly reduce the impact of ICS while introducing other biases, we are able to have a surgical view at the effects ICS has on training neural networks. Our experiments show that ICS has a weight regularizing effect on models, and completely removing it enables for faster convergence of the neural network.
BibTeX
@article{Stoica_Simionescu_2024, title={Backforward Propagation (Student Abstract)}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/27029}, DOI={10.1609/aaai.v37i13.27029}, abstractNote={In this paper we introduce Backforward Propagation, a method of completely eliminating Internal Covariate Shift (ICS). Unlike previous methods, which only indirectly reduce the impact of ICS while introducing other biases, we are able to have a surgical view at the effects ICS has on training neural networks. Our experiments show that ICS has a weight regularizing effect on models, and completely removing it enables for faster convergence of the neural network.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Stoica, George and Simionescu, Cristian}, year={2024}, month={Jul.}, pages={16338-16339} }