Search Results for author: Filipe Assunção

Found 8 papers, 3 papers with code

Natural language to SQL in low-code platforms

no code implementations29 Aug 2023 Sofia Aparicio, Samuel Arcadinho, João Nadkarni, David Aparício, João Lages, Mariana Lourenço, Bartłomiej Matejczyk, Filipe Assunção

Alongside this, we describe the entire pipeline, which comprises a feedback loop that allows us to quickly collect production data and use it to retrain our SQL generation model.

AutoLR: An Evolutionary Approach to Learning Rate Policies

no code implementations8 Jul 2020 Pedro Carvalho, Nuno Lourenço, Filipe Assunção, Penousal Machado

This work presents AutoLR, a framework that evolves Learning Rate Schedulers for a specific Neural Network Architecture using Structured Grammatical Evolution.

Evolution of Scikit-Learn Pipelines with Dynamic Structured Grammatical Evolution

1 code implementation1 Apr 2020 Filipe Assunção, Nuno Lourenço, Bernardete Ribeiro, Penousal Machado

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 algorithm and its parameterisation.

AutoML BIG-bench Machine Learning +1

Incremental Evolution and Development of Deep Artificial Neural Networks

1 code implementation1 Apr 2020 Filipe Assunção, Nuno Lourenço, Bernardete Ribeiro, Penousal Machado

Despite aiding non-expert users to design and train ANNs, the vast majority of NE approaches disregard the knowledge that is gathered when solving other tasks, i. e., evolution starts from scratch for each problem, ultimately delaying the evolutionary process.

Automatic Design of Artificial Neural Networks for Gamma-Ray Detection

no code implementations9 May 2019 Filipe Assunção, João Correia, Rúben Conceição, Mário Pimenta, Bernardo Tomé, Nuno Lourenço, Penousal Machado

The results show that the best CNN generated by Fast-DENSER++ improves by a factor of 2 when compared with the results reported by classic statistical approaches.

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

no code implementations8 May 2019 Filipe Assunção, Nuno Lourenço, Penousal Machado, Bernardete Ribeiro

This paper proposes a new extension to Deep Evolutionary Network Structured Evolution (DENSER), called Fast-DENSER++ (F-DENSER++).

DENSER: Deep Evolutionary Network Structured Representation

17 code implementations4 Jan 2018 Filipe Assunção, Nuno Lourenço, Penousal Machado, Bernardete Ribeiro

Deep Evolutionary Network Structured Representation (DENSER) is a novel approach to automatically design Artificial Neural Networks (ANNs) using Evolutionary Computation.

Data Augmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.