Sgornn: Combining scalar gates and orthogonal constraints in recurrent networks

DOI10.1016/J.NEUNET.2022.11.028MaRDI QIDQ6488746

Will Taylor-Melanson, Stan Matwin, Martha Dais Ferreira

Publication date: 18 October 2023

Published in: Neural Networks (Search for Journal in Brave)

zbMATH Keywords

recurrent neural networksunitary matricesdeep learningexploding gradient problem

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cites Work

• 10.1162/153244303321897690
• Gated Orthogonal Recurrent Units: On Learning to Forget
• Advanced Lectures on Machine Learning

This page was built for publication: Sgornn: Combining scalar gates and orthogonal constraints in recurrent networks