Date


Download Available

101 results

Learning Descriptors for Novelty-Search Based Instance Generation via Meta-evolution

Conference Proceeding
Marrero, A., Segredo, E., León, C., & Hart, E. (in press)
Learning Descriptors for Novelty-Search Based Instance Generation via Meta-evolution. In Genetic and Evolutionary Computation Conference (GECCO ’24), July 14–18, 2024, Melbourne, VIC, Australia. https://doi.org/10.1145/3638529.3654028
The ability to generate example instances from a domain is important in order to benchmark algorithms and to generate data that covers an instance-space in order to train mach...

A Hierarchical Approach to Evolving Behaviour-Trees for Swarm Control

Conference Proceeding
Montague, K., Hart, E., & Paechter, B. (2024)
A Hierarchical Approach to Evolving Behaviour-Trees for Swarm Control. In S. Smith, J. Correia, & C. Cintrano (Eds.), Applications of Evolutionary Computation: 27th European Conference, EvoApplications 2024, Held as Part of EvoStar 2024, Aberystwyth, UK, April 3–5, 2024, Proceedings, Part I (178-193). https://doi.org/10.1007/978-3-031-56852-7_12
Behaviour trees (BTs) are commonly used as controllers in robotic swarms due their modular composition and to the fact that they can be easily interpreted by humans. From an a...

On the Utility of Probing Trajectories for Algorithm-Selection

Conference Proceeding
Renau, Q., & Hart, E. (2024)
On the Utility of Probing Trajectories for Algorithm-Selection. In Applications of Evolutionary Computation. EvoApplications 2024 (98-114). https://doi.org/10.1007/978-3-031-56852-7_7
Machine-learning approaches to algorithm-selection typically take data describing an instance as input. Input data can take the form of features derived from the instance desc...

Generalized Early Stopping in Evolutionary Direct Policy Search

Journal Article
Arza, E., Le Goff, L. K., & Hart, E. (in press)
Generalized Early Stopping in Evolutionary Direct Policy Search. ACM Transactions on Evolutionary Learning and Optimization, https://doi.org/10.1145/3653024
Lengthy evaluation times are common in many optimization problems such as direct policy search tasks, especially when they involve conducting evaluations in the physical world...

Synthesising Diverse and Discriminatory Sets of Instances using Novelty Search in Combinatorial Domains

Journal Article
Marrero, A., Segredo, E., Leon, C., & Hart, E. (in press)
Synthesising Diverse and Discriminatory Sets of Instances using Novelty Search in Combinatorial Domains. Evolutionary Computation,
Gathering sufficient instance data to either train algorithm-selection models or understand algorithm footprints within an instance space can be challenging. We propose an app...

Evolving Behavior Allocations in Robot Swarms

Conference Proceeding
Hallauer, S., Nitschke, G., & Hart, E. (2024)
Evolving Behavior Allocations in Robot Swarms. In 2023 IEEE Symposium Series on Computational Intelligence (SSCI) (1526-1531). https://doi.org/10.1109/SSCI52147.2023.10371934
Behavioral diversity is known to benefit problem-solving in biological social systems such as insect colonies and human societies, as well as in artificial distributed systems...

Evaluation of Frameworks That Combine Evolution and Learning to Design Robots in Complex Morphological Spaces

Journal Article
Li, W., Buchanan, E., Goff, L. K. L., Hart, E., Hale, M. F., Wei, B., …Tyrrell, A. M. (in press)
Evaluation of Frameworks That Combine Evolution and Learning to Design Robots in Complex Morphological Spaces. IEEE Transactions on Evolutionary Computation, https://doi.org/10.1109/tevc.2023.3316363
Jointly optimising both the body and brain of a robot is known to be a challenging task, especially when attempting to evolve designs in simulation that will subsequently be b...

Automated Algorithm Selection: from Feature-Based to Feature-Free Approaches

Journal Article
Alissa, M., Sim, K., & Hart, E. (in press)
Automated Algorithm Selection: from Feature-Based to Feature-Free Approaches. Journal of Heuristics, https://doi.org/10.1007/s10732-022-09505-4
We propose a novel technique for algorithm-selection, applicable to optimisation domains in which there is implicit sequential information encapsulated in the data, e.g., in o...

Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers

Conference Proceeding
Cardoso, R. P., Hart, E., Burth Kurka, D., & Pitt, J. (2022)
Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers. In Applications of Evolutionary Computation: EvoApplications 2022 (418-434). https://doi.org/10.1007/978-3-031-02462-7_27
Using Neuroevolution combined with Novelty Search to promote behavioural diversity is capable of constructing high-performing ensembles for classification. However, using grad...

Lifelong Learning Machines: Towards Developing Optimisation Systems That Continually Learn

Book Chapter
Hart, E. (2022)
Lifelong Learning Machines: Towards Developing Optimisation Systems That Continually Learn. In A. E. Smith (Ed.), Women in Computational Intelligence: Key Advances and Perspectives on Emerging Topics (187-203). Cham: Springer. https://doi.org/10.1007/978-3-030-79092-9_9
Standard approaches to developing optimisation algorithms tend to involve selecting an algorithm and tuning it to work well on a large set of problem instances from the domain...
16 results

Swarmchestrate - Application-level Swarm-based Orchestration Across the Cloud-to-Things Continuum

2024 - 2026
The next-generation of intelligent cyber-physical and IoT systems powered by artificial intelligence (AI) are becoming an essential part of our environment. With the ever-growing number of intelligent...
Funder: European Commission | Value: £357,303

Keep Learning

2021 - 2024
The project proposes a novel architecture for designing optimisation systems that “keeps learning” when exposed to a continual stream of instances: these systems will autonomously adapt their compone...
Funder: Engineering and Physical Sciences Research Council | Value: £388,219

COG-MHEAR: Towards cognitively-inspired, 5G-IoT enabled multi-modal hearing aids

2021 - 2026
Embracing the multimodal nature of speech presents both opportunities and challenges for hearing assistive technology: on the one hand there are opportunities for the design of new multimodal audio-vi...
Funder: Engineering and Physical Sciences Research Council | Value: £3,258,999

Improving Science-Informed Crab Fisheries Management in Brazil

2020 - 2021
The project offers a unique opportunity to engage with, actively contribute to and learn from a UK-Brazilian applied research project investigating the reproductive rhythmicity of the mangrove crab Uc...
Funder: Natural Environment Research Council | Value: £2,900

Hyperheuristics for infrastructure system optimisation

2020 - 2020
Continuum Industries novel software tech allows engineers to automate their work and evaluate millions of possible combinations of design parameters. Primary application lies in linear infrastructure ...
Funder: Data Lab | Value: £19,599

Towards Guided Self-Organisation in Artificial Complex Systems: A Swarm Robotics Case Study

2020 - 2024
Swarm robotics refers to the design and coordination of large numbers of simple physical robots. Uses include environmental applications such as pollution monitoring in the oceans using aquatic robots...
Funder: Royal Society | Value: £11,500

KTP: Intelligent Agents

2019 - 2022
Improving customer experience through intelligent workflow
Funder: Innovate UK | Value: £268,152

Autonomous Robot Evolution: Cradle to Grave

2018 - 2022
Robotics is changing the landscape of innovation. But traditional design approaches are not suited to novel or unknown habitats and contexts, for instance: robot colonies for ore mining, exploring or ...
Funder: Engineering and Physical Sciences Research Council | Value: £366,412

Ensembles for Optimisation

2015 - 2016
Optimisation – finding cost-effective or high-performing solutions - is a key economic driver for business today. However, academic literature on search-based optimisation techniques reflects an escal...
Funder: Leverhulme Trust | Value: £34,465

FOCAS

2013 - 2016
FOCAS is a coordination action in the area of collective adaptive systems. It provides increased visibility to the research carried out by projects funded by the FOCAS FET Proactive Initiative and oth...
Funder: European Commission | Value: £639,999
13 results

Prof. Emma Hart invited to join Scottish Government Steering Group to develop an Artificial Intelligence (AI) strategy for Scotland.

16 September 2019
Prof. Emma Hart has been invited by Minister Kate Forbes to join a Scottish Government Steering Group to develop an Artificial Intelligence (AI) strategy for Scotland.

Researchers from Nature-Inspired Intelligent Systems group win Best Paper Award@GECCO 2019

16 July 2019
PhD student Mohamad Alissa with supervisors Dr Kevin Sim and Prof. Emma Hart won the Best Paper award in the ECOM track at GECCO 2019 in Prague for their paper: Algorithm Selection Using Deep Learnin...

Prof . Emma Hart gives interview "An Insider's Guide to Evolutionary Computation"

17 December 2018
Laura van Beers from ContactEngine, a London based company delivering software that enables its customers to proactively engage customers in AI-driven conversations to fulfil their business objective...

Prof. Emma Hart invited to talk at Scotland IS Software Engineering Leader's Forum to discuss SICSA's work on AI

20 November 2018
Prof. Emma Hart gave an invited talk at the monthly meet-up of the Scotland IS Software Engineering forum on behalf of the SICSA AI theme to describe the work taking place across Scottish Universities...

Prof. Emma Hart interviewed in new video released by Sentient AI to provide unique insights to business leaders on the growing applicability of evolutionary computation

13 August 2018
Sentient Technologies, a world leader in artificial intelligence (AI) products based on evolutionary computation, today announced a new video collection that provides unique insights to the burgeonin...

Prof. Emma Hart and Dr Kevin Sim win Bronze Award in International Humies competition for work on predicting wind damage in Forestry

18 July 2018
The Annual Humies prize is awarded at the International Conference on Genetic and Evolutionary Computation for human-competitive results that have been produced by any form of genetic and evolutionar...

Evolutionary Robotics Research Nominated for Best Paper Award

14 July 2018
Prof. Emma Hart, Dr Andreas Steyven and Prof. Ben Paechter have been nominated for a prestigious best paper award at the GECCO 18, Kyoto, Japan for new work in evolving a diverse team of swarm robot...

Prof. Emma Hart invited as a keynote speaker at IJCCI in Funchal, Madeira, November 2017

1 November 2017
The International Joint Conference on Computational Intelligence brings together researchers, engineers and practitioners interested in the field of Computational Intelligence both from theoretical an...

CAVES researchers have 3 papers accepted at GECCO 2017

14 July 2017
Members of the CAVES research group have 3 papers accepted at the world's leading conference on Evolutionary Computing. GECCO 2017 will be held in Berlin from 15-19th July 2017. Accepted papers are: ...

Prof. Emma Hart interview with MIT Press on her new Editor-in-Chief role

17 February 2017
The New Year welcomed Emma Hart to the helm of Evolutionary Computation. She took over the role of Editor-in-Chief from Hans-Georg Beyer (who had assumed the role himself in 2010). Professor Hart ans...