no code implementations • 4 Jan 2024 • Marcos Eduardo Valle, Wington L. Vital, Guilherme Vieira
However, hypercomplex-valued neural networks are a type of vector-valued neural network defined on an algebra with additional algebraic or geometric properties.
no code implementations • 11 Oct 2023 • Guilherme Vieira, Eleonora Grassucci, Marcos Eduardo Valle, Danilo Comminiello
To overcome these limitations, we employ a dual quaternion representation of rigid motions in the 3D space that jointly describes rotations and translations of point sets, processing each of the points as a single entity.
no code implementations • 6 Sep 2022 • Wington L. Vital, Guilherme Vieira, Marcos Eduardo Valle
The universal approximation theorem asserts that a single hidden layer neural network approximates continuous functions with any desired precision on compact sets.
1 code implementation • 26 May 2022 • Guilherme Vieira, Marcos Eduardo Valle
This paper features convolutional neural networks defined on hypercomplex algebras applied to classify lymphocytes in blood smear digital microscopic images.
no code implementations • 15 Jan 2021 • Guilherme Vieira, Marcos Eduardo Valle
This paper aims to establish a framework for extreme learning machines (ELMs) on general hypercomplex algebras.