no code implementations • 12 Apr 2024 • Fergal Stapleton, Edgar Galván
This efficiency advantage adds to the overall appeal of our proposed NeuroLGP-SM in optimising the configuration of large DNNs.
no code implementations • 28 Mar 2024 • Fergal Stapleton, Brendan Cody-Kenny, Edgar Galván
The amalgamation of these two techniques culminates in our proposed methodology known as the NeuroLGP-Surrogate Model (NeuroLGP-SM).
no code implementations • 4 Aug 2023 • Edgar Galván, Fergal Stapleton
Two well-known and robust Evolutionary Multi-objective Optimisation (EMO) algorithms, NSGA-II and MOEA/D are also adopted.
no code implementations • 5 May 2023 • Fergal Stapleton, Edgar Galván
This refers to the use of evolutionary algorithms in the automatic configuration of artificial neural network (ANN) architectures, hyper-parameters and/or the training of ANNs.
no code implementations • 10 Jun 2022 • Edgar Galván, Leonardo Trujillo, Fergal Stapleton
Semantics is a growing area of research in Genetic programming (GP) and refers to the behavioural output of a Genetic Programming individual when executed.
no code implementations • 4 May 2022 • Fergal Stapleton, Edgar Galván, Ganesh Sistu, Senthil Yogamani
The incentive for using Evolutionary Algorithms (EAs) for the automated optimization and training of deep neural networks (DNNs), a process referred to as neuroevolution, has gained momentum in recent years.
no code implementations • 6 May 2021 • Edgar Galván, Leonardo Trujillo, Fergal Stapleton
This is then used to compute a distance between the pivot and every individual in the population.
no code implementations • 28 Feb 2021 • Fergal Stapleton, Edgar Galván
We show, for the first time, how we can promote semantic diversity in MOEA/D in Genetic Programming.
no code implementations • 8 Dec 2020 • Edgar Galván, Fergal Stapleton
The study of semantics in Genetic Program (GP) deals with the behaviour of a program given a set of inputs and has been widely reported in helping to promote diversity in GP for a range of complex problems ultimately improving evolutionary search.
no code implementations • 25 Sep 2020 • Edgar Galván, Fergal Stapleton
We empirically and consistently show how by naturally handling semantic distance as an additional criterion to be optimised in MOGP leads to better performance when compared to canonical methods and SSC.