activity
20172023
most citedTowards the Evolution of Multi-Layered Neural Networks: A Dynamic Structured Grammatical Evolution Approach

20 citations · 34 across the 4 of their papers we have counts for

collaborators

7 papers

cs.AI20231 cited

Natural language to SQL in low-code platforms

Sofia Aparicio, Samuel Arcadinho, João Nadkarni +5

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 natur…

cs.NE20207 cited

AutoLR: An Evolutionary Approach to Learning Rate Policies

Pedro Carvalho, Nuno Lourenço, Filipe Assunção +1

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 fin…

cs.NE2020

Evolution of Scikit-Learn Pipelines with Dynamic Structured Grammatical Evolution

Filipe Assunção, Nuno Lourenço, Bernardete Ribeiro +1

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…

cs.NE2020

Incremental Evolution and Development of Deep Artificial Neural Networks

Filipe Assunção, Nuno Lourenço, Bernardete Ribeiro +1

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 t…

cs.NE2019

Automatic Design of Artificial Neural Networks for Gamma-Ray Detection

Filipe Assunção, João Correia, Rúben Conceição +4

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 propo…

cs.NE20196 cited

Fast-DENSER++: Evolving Fully-Trained Deep Artificial Neural Networks

Filipe Assunção, Nuno Lourenço, Penousal Machado +1

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…