Search Results for author:
Found 13 papers, 2 papers with code
Evolution of a Functionally Diverse Swarm via a Novel Decentralised Quality-Diversity Algorithm
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.
Optimisation and Illumination of a Real-world Workforce Scheduling and Routing Application via Map-Elites
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.
An Investigation of Environmental Influence on the Benefits of Adaptation Mechanisms in Evolutionary Swarm Robotics
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.
Morpho-evolution with learning using a controller archive as an inheritance mechanism
This causes a potential mismatch between the structure of an inherited controller and the new body.
Comparison of atlas-based and neural-network-based semantic segmentation for DENSE MRI images
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.
Improving the Naturalness and Diversity of Referring Expression Generation models using Minimum Risk Training
In this paper we consider the problem of optimizing neural Referring Expression Generation (REG) models with sequence level objectives.
Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers
Using Neuroevolution combined with Novelty Search to promote behavioural diversity is capable of constructing high-performing ensembles for classification.
Automated Algorithm Selection: from Feature-Based to Feature-Free Approaches
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.
To Switch or not to Switch: Predicting the Benefit of Switching between Algorithms based on Trajectory Features
These features are then used to predict what algorithm to switch to.
Generalized Early Stopping in Evolutionary Direct Policy Search
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.
On the Utility of Probing Trajectories for Algorithm-Selection
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.
Understanding fitness landscapes in morpho-evolution via local optima networks
Morpho-evolution (ME) refers to the simultaneous optimisation of a robot's design and controller to maximise performance given a task and environment.
Improving Algorithm-Selection and Performance-Prediction via Learning Discriminating Training Samples
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.
