26 citations · 65 across the 8 of their papers we have counts for
8 papers
Ghost Features and Spooky Transfer Learning for Hypercomplex-Valued Neural Networks
Guilherme Vieira Neto, Marcos Eduardo Valle
Hypercomplex numbers extend the concept of complex numbers by introducing additional imaginary components. Besides increasing dimensionality, operations on the imaginary parts prov…
V-EfficientNets: Vector-Valued Efficiently Scaled Convolutional Neural Network Models
Guilherme Vieira Neto, Marcos Eduardo Valle
EfficientNet models are convolutional neural networks optimized for parameter allocation by jointly balancing network width, depth, and resolution. Renowned for their exceptional a…
Dynamics of Structured Complex-Valued Hopfield Neural Networks
Rama Murthy Garimella, Marcos Eduardo Valle, Guilherme Vieira +2
In this paper, we explore the dynamics of structured complex-valued Hopfield neural networks (CvHNNs), which arise when the synaptic weight matrix possesses specific structural pro…
Universal Approximation Theorem for Vector- and Hypercomplex-Valued Neural Networks
Marcos Eduardo Valle, Wington L. Vital, Guilherme Vieira
The universal approximation theorem states that a neural network with one hidden layer can approximate continuous functions on compact sets with any desired precision. This theorem…
Dual Quaternion Rotational and Translational Equivariance in 3D Rigid Motion Modelling
Guilherme Vieira, Eleonora Grassucci, Marcos Eduardo Valle +1
Objects' rigid motions in 3D space are described by rotations and translations of a highly-correlated set of points, each with associated coordinates that real-valued netwo…
Extending the Universal Approximation Theorem for a Broad Class of Hypercomplex-Valued Neural Networks
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. As an existentia…
Acute Lymphoblastic Leukemia Detection Using Hypercomplex-Valued Convolutional Neural Networks
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. Such classification is…
A General Framework for Hypercomplex-valued Extreme Learning Machines
Guilherme Vieira, Marcos Eduardo Valle
This paper aims to establish a framework for extreme learning machines (ELMs) on general hypercomplex algebras. Hypercomplex neural networks are machine learning models that featur…