Zobrazeno 1 - 10
of 43
pro vyhledávání: '"de Rosa, Gustavo H."'
The continuous computational power growth in the last decades has made solving several optimization problems significant to humankind a tractable task; however, tackling some of them remains a challenge due to the overwhelming amount of candidate sol
Externí odkaz:
http://arxiv.org/abs/2301.13671
Machine Learning algorithms have been extensively researched throughout the last decade, leading to unprecedented advances in a broad range of applications, such as image classification and reconstruction, object recognition, and text categorization.
Externí odkaz:
http://arxiv.org/abs/2212.09447
Autor:
Roder, Mateus, Almeida, Jurandy, de Rosa, Gustavo H., Passos, Leandro A., Rossi, André L. D., Papa, João P.
In the last decade, exponential data growth supplied machine learning-based algorithms' capacity and enabled their usage in daily-life activities. Additionally, such an improvement is partially explained due to the advent of deep learning techniques,
Externí odkaz:
http://arxiv.org/abs/2211.17045
Publikováno v:
In Applied Soft Computing October 2024 164
Autor:
Javaheripi, Mojan, de Rosa, Gustavo H., Mukherjee, Subhabrata, Shah, Shital, Religa, Tomasz L., Mendes, Caio C. T., Bubeck, Sebastien, Koushanfar, Farinaz, Dey, Debadeepta
The Transformer architecture is ubiquitously used as the building block of large-scale autoregressive language models. However, finding architectures with the optimal trade-off between task performance (perplexity) and hardware constraints like peak
Externí odkaz:
http://arxiv.org/abs/2203.02094
Autor:
de Rosa, Gustavo H., Papa, João Paulo
A graph-inspired classifier, known as Optimum-Path Forest (OPF), has proven to be a state-of-the-art algorithm comparable to Logistic Regressors, Support Vector Machines in a wide variety of tasks. Recently, its Python-based version, denoted as OPFyt
Externí odkaz:
http://arxiv.org/abs/2106.11828
Autor:
Roder, Mateus, de Rosa, Gustavo H., de Albuquerque, Victor Hugo C., Rossi, André L. D., Papa, João P.
Deep learning architectures have been widely fostered throughout the last years, being used in a wide range of applications, such as object recognition, image reconstruction, and signal processing. Nevertheless, such models suffer from a common probl
Externí odkaz:
http://arxiv.org/abs/2101.06741
Publikováno v:
APPLIED SOFT COMPUTING; v. 94, SEP 2020
Feature selection for a given model can be transformed into an optimization task. The essential idea behind it is to find the most suitable subset of features according to some criterion. Nature-inspired optimization can mitigate this problem by prod
Externí odkaz:
http://arxiv.org/abs/2101.05652
Machine Learning has been applied in a wide range of tasks throughout the last years, ranging from image classification to autonomous driving and natural language processing. Restricted Boltzmann Machine (RBM) has received recent attention and relies
Externí odkaz:
http://arxiv.org/abs/2101.01042
Optimization aims at selecting a feasible set of parameters in an attempt to solve a particular problem, being applied in a wide range of applications, such as operations research, machine learning fine-tuning, and control engineering, among others.
Externí odkaz:
http://arxiv.org/abs/1912.13002