Tensor-based framework for training flexible neural networks

no code implementations • 25 Jun 2021 • Yassine Zniyed, Konstantin Usevich, Sebastian Miron, David Brie

Activation functions (AFs) are an important part of the design of neural networks (NNs), and their choice plays a predominant role in the performance of a NN.

A general framework for constrained convex quaternion optimization

no code implementations • 4 Feb 2021 • Julien Flamant, Sebastian Miron, David Brie

This paper introduces a general framework for solving constrained convex quaternion optimization problems in the quaternion domain.

Optimization and Control Signal Processing