no code implementations • INLG (ACL) 2020 • Nikolaos Panagiaris, Emma Hart, Dimitra Gkatzia
In this paper we consider the problem of optimizing neural Referring Expression Generation (REG) models with sequence level objectives.
no code implementations • 8 Apr 2024 • Quentin Renau, Emma Hart
The algorithm-configuration tool irace is used to tune the parameters of a simple Simulated Annealing algorithm (SA) to produce trajectories that maximise the performance metrics of ML models trained on this data.
no code implementations • 12 Feb 2024 • Sarah L. Thomson, Léni K. Le Goff, Emma Hart, Edgar Buchanan
Morpho-evolution (ME) refers to the simultaneous optimisation of a robot's design and controller to maximise performance given a task and environment.
no code implementations • 23 Jan 2024 • Quentin Renau, Emma Hart
Input data can take the form of features derived from the instance description or fitness landscape, or can be a direct representation of the instance itself, i. e. an image or textual description.
1 code implementation • 7 Aug 2023 • Etor Arza, Leni K. Le Goff, Emma Hart
We test the introduced stopping criterion in five direct policy search environments drawn from games, robotics and classic control domains, and show that it can save up to 75% of the computation time.
no code implementations • 17 Feb 2023 • Diederick Vermetten, Hao Wang, Kevin Sim, Emma Hart
These features are then used to predict what algorithm to switch to.
no code implementations • 24 Mar 2022 • Mohamad Alissa, Kevin Sim, Emma Hart
This contrasts to typical approaches to algorithm-selection which require a model to be trained using domain-specific instance features that need to be first derived from the input data.
no code implementations • 30 Jan 2022 • Rui P. Cardoso, Emma Hart, David Burth Kurka, Jeremy V. Pitt
Using Neuroevolution combined with Novelty Search to promote behavioural diversity is capable of constructing high-performing ensembles for classification.
no code implementations • 29 Sep 2021 • Elle Buser, Emma Hart, Ben Huenemann
Two segmentation methods, one atlas-based and one neural-network-based, were compared to see how well they can each automatically segment the brain stem and cerebellum in Displacement Encoding with Stimulated Echoes Magnetic Resonance Imaging (DENSE-MRI) data.
no code implementations • 9 Apr 2021 • Léni K. Le Goff, Edgar Buchanan, Emma Hart, Agoston E. Eiben, Wei Li, Matteo De Carlo, Alan F. Winfield, Matthew F. Hale, Robert Woolley, Mike Angus, Jon Timmis, Andy M. Tyrrell
This causes a potential mismatch between the structure of an inherited controller and the new body.
no code implementations • 29 May 2018 • Neil Urquhart, Emma Hart
The first is to evaluate whether ME can provide solutions of competitive quality to an Evolutionary Algorithm (EA) in terms of a single objective function, and the second to examine its ability to provide a repertoire of solutions that maximise user choice.
no code implementations • 20 Apr 2018 • Andreas Steyven, Emma Hart, Ben Paechter
In this paper, we address this question by analysing the performance of a swarm in a range of simulated, dynamic environments where a distributed evolutionary algorithm for evolving a controller is augmented with a number of different individual learning mechanisms.
1 code implementation • 20 Apr 2018 • Emma Hart, Andreas S. W. Steyven, Ben Paechter
The presence of functional diversity within a group has been demonstrated to lead to greater robustness, higher performance and increased problem-solving ability in a broad range of studies that includes insect groups, human groups and swarm robotics.