← Back to papers
Classical and Quantum Algorithms for Orthogonal Neural Networks
Iordanis Kerenidis, Jonas Landman, Natansh Mathur·June 14, 2021
Physics
AI Breakdown
Get a structured breakdown of this paper — what it's about, the core idea, and key takeaways for the field.
Abstract
Orthogonal neural networks have recently been introduced as a new type of neural networks imposing orthogonality on the weight matrices. They could achieve higher accuracy and avoid evanescent or explosive gradients for deep architectures. Several classical gradient descent methods have been proposed to preserve orthogonality while updating the weight matrices