User: Guest  Login
Title:

Neural Network Training with Safe Regularization in the Null Space of Batch Activations

Document type:
Konferenzbeitrag
Contribution type:
Textbeitrag / Aufsatz
Author(s):
Matthias Kissel, Martin Gottwald, Klaus Diepold
Abstract:
We propose to formulate the training of neural networks with side optimization goals, such as obtaining structured weight matrices, as lexicographic optimization problem. The lexicographic order can be maintained during training by optimizing the side-optimization goal exclusively in the null space of batch activations. We call the resulting training method Safe Regularization, because the side optimization goal can be safely integrated into the training with limited influence on the main optimi...     »
Book / Congress title:
International Conference on Artificial Neural Networks
Year:
2020
Reviewed:
ja
TUM Institution:
Lehrstuhl für Datenverarbeitung
 BibTeX