Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Assunção, Filipe"'
Autor:
Aparicio, Sofia, Arcadinho, Samuel, Nadkarni, João, Aparício, David, Lages, João, Lourenço, Mariana, Matejczyk, Bartłomiej, Assunção, Filipe
One of the developers' biggest challenges in low-code platforms is retrieving data from a database using SQL queries. Here, we propose a pipeline allowing developers to write natural language (NL) to retrieve data. In this study, we collect, label, a
Externí odkaz:
http://arxiv.org/abs/2308.15239
Autor:
Lourenço, Hugo, Seco, João Costa, Ferreira, Carla, Simões, Tiago, Silva, Vasco, Assunção, Filipe, Menezes, André
In model-driven engineering, the bidirectional transformation of models plays a crucial role in facilitating the use of editors that operate at different levels of abstraction. This is particularly important in the context of industrial-grade low-cod
Externí odkaz:
http://arxiv.org/abs/2305.03361
The choice of a proper learning rate is paramount for good Artificial Neural Network training and performance. In the past, one had to rely on experience and trial-and-error to find an adequate learning rate. Presently, a plethora of state of the art
Externí odkaz:
http://arxiv.org/abs/2007.04223
The deployment of Machine Learning (ML) models is a difficult and time-consuming job that comprises a series of sequential and correlated tasks that go from the data pre-processing, and the design and extraction of features, to the choice of the ML a
Externí odkaz:
http://arxiv.org/abs/2004.00307
NeuroEvolution (NE) methods are known for applying Evolutionary Computation to the optimisation of Artificial Neural Networks(ANNs). Despite aiding non-expert users to design and train ANNs, the vast majority of NE approaches disregard the knowledge
Externí odkaz:
http://arxiv.org/abs/2004.00302
Autor:
Assunção, Filipe, Correia, João, Conceição, Rúben, Pimenta, Mário, Tomé, Bernardo, Lourenço, Nuno, Machado, Penousal
Publikováno v:
in IEEE Access, vol. 7, pp. 110531-110540, 2019
The goal of this work is to investigate the possibility of improving current gamma/hadron discrimination based on their shower patterns recorded on the ground. To this end we propose the use of Convolutional Neural Networks (CNNs) for their ability t
Externí odkaz:
http://arxiv.org/abs/1905.03532
This paper proposes a new extension to Deep Evolutionary Network Structured Evolution (DENSER), called Fast-DENSER++ (F-DENSER++). The vast majority of NeuroEvolution methods that optimise Deep Artificial Neural Networks (DANNs) only evaluate the can
Externí odkaz:
http://arxiv.org/abs/1905.02969
Deep Evolutionary Network Structured Representation (DENSER) is a novel approach to automatically design Artificial Neural Networks (ANNs) using Evolutionary Computation. The algorithm not only searches for the best network topology (e.g., number of
Externí odkaz:
http://arxiv.org/abs/1801.01563
Current grammar-based NeuroEvolution approaches have several shortcomings. On the one hand, they do not allow the generation of Artificial Neural Networks (ANNs composed of more than one hidden-layer. On the other, there is no way to evolve networks
Externí odkaz:
http://arxiv.org/abs/1706.08493
Autor:
Assunção, Filipe Guerreiro
Publikováno v:
Repositório Científico de Acesso Aberto de Portugal
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Doctoral thesis submitted in partial fulfllment of the Doctoral Program in Information Science and Technology and presented to the Department of Informatics Engineering of the Faculty of Sciences and Technology of the University of Coimbra. Artificia
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e3ee3e7bfe130e9f7642794b186f2ea4