Backforward Propagation (Student Abstract)

Authors

  • George Stoica "Alexandru Ioan Cuza" University, Iasi, Romania
  • Cristian Simionescu "Alexandru Ioan Cuza" University, Iasi, Romania

DOI:

https://doi.org/10.1609/aaai.v37i13.27029

Keywords:

Optimization, Internal Covariate Shift, Backpropagation, Regularization

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.
AAAI-23 Proceedings Cover

Downloads

Published

2024-07-15

How to Cite

Stoica, G., & Simionescu, C. (2024). Backforward Propagation (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16338-16339. https://doi.org/10.1609/aaai.v37i13.27029

Issue

Vol. 37 No. 13: AAAI-23 Special Programs, IAAI-23, EAAI-23, Student Papers and Demonstrations

Section

AAAI Student Abstract and Poster Program