23 results

Date


Download Available

223 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...

How Much do Robots Understand Rudeness? Challenges in Human-Robot Interaction

Conference Proceeding
Orme, M., Yu, Y., & Tan, Z. (in press)
How Much do Robots Understand Rudeness? Challenges in Human-Robot Interaction.
This paper concerns the pressing need to understand and manage inappropriate language within the evolving human-robot interaction (HRI) landscape. As intelligent systems and r...

Can Federated Models Be Rectified Through Learning Negative Gradients?

Conference Proceeding
Tahir, A., Tan, Z., & Babaagba, K. O. (2024)
Can Federated Models Be Rectified Through Learning Negative Gradients?. In Big Data Technologies and Applications (18-32). https://doi.org/10.1007/978-3-031-52265-9_2
Federated Learning (FL) is a method to train machine learning (ML) models in a decentralised manner, while preserving the privacy of data from multiple clients. However, FL is...

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...

Too Constrained for Genetic Algorithms. Too Hard for Evolutionary Computing. The Traveling Tournament Problem.

Conference Proceeding
Verduin, K., Thomson, S. L., & van den Berg, D. (2023)
Too Constrained for Genetic Algorithms. Too Hard for Evolutionary Computing. The Traveling Tournament Problem. In Proceedings of the 15th International Joint Conference on Computational Intelligence (246-257). https://doi.org/10.5220/0012192100003595
Unlike other NP-hard problems, the constraints on the traveling tournament problem are so pressing that it’s hardly possible to randomly generate a valid solution, for example...
31 results

False webs: Network to address the misinformation pandemic

2023 - 2025
Fake news (inaccurate information) peaked during the pandemic with around 46 000 daily Twitter posts containing false information (Lupi, 2020). In Europe over 70% people regularly encounter fake news ...
Funder: Royal Society of Edinburgh | Value: £19,931

Cloud based distribution system to tackle food poverty

2022 - 2023
Local food sectors, e.g. Foodbanks, still rely on paper-based referral systems whilst continuing to see increasing demand. In addition, the model of direct hand-outs of food parcels and electricity vo...
Funder: Scottish Funding Council | Value: £570

AI for Plant Image Analysis: where we are and whats next?

2021 - 2023
The workshop has two aims: (i) offering training sessions on how to develop deep networks to people involved in plant biology; (ii) analyse their current provision
Funder: The University of Nottingham | Value: £5,400

A Reinforcement Learning Based Resource Management System for Long Term Care for Elderly People

2021 - 2024
A reinforcement learning method will model the behaviour of community care organisations with sequential decision processes focusing on organising the distribution, procurement and management of daily...
Funder: Royal Society of Edinburgh | Value: £11,200

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

KTP Ace Aquatec

2021 - 2023
To develop, test and incorporate Innovative AI based approaches to improve accuracy of Individual fish identification and sea lice detection.
Funder: Innovate UK | Value: £265,334

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

Bus Passenger Analytics

2020 - 2020
Passengers using the Lothian Buses network may use a smart card (Ridacard) to pay for their journey, swiping the card on boarding a vehicle. Smart card journeys account for about 1/3rd of journeys mad...
Funder: Data Lab | Value: £26,170

Extending a microservices architecture to support user functions and provide cloud APIs

2019 - 2020
Extending a containerised microservices architecture developed in the initial project to support a set of user functions required for the platform's MVP. Additionally, the project will deliver cloud A...
Funder: Scottish Funding Council | Value: £14,250

Optimisation of AirNode mesh nets

2019 - 2020
Urban air quality affects the lives of millions, according to WHO statistics air quality contributes to 6.7% of all deaths worldwide. Managing air quality in urban areas is now a priority for governme...
Funder: Scottish Funding Council | Value: £5,000
8 results

Application of evolutionary machine learning in metamorphic malware analysis and detection

2017 - 2021
Dr Kehinde Babaagba | Director of Studies: Dr Thomas Tan | Second Supervisor: Prof Emma Hart

Towards real-time cognitively-inspired multi-modal speech separation: Novel architectures and algorithms

2016 - 2021
Dr. Mandar Gogate | Director of Studies: Prof Amir Hussain | Second Supervisor: Prof Ahmed Al-Dubai

Evolving planar mechanisms for the conceptual stage of mechanical design

2015 - 2020
Dr Paul Lapok | Director of Studies: Alistair Lawson | Second Supervisor: Prof Ben Paechter

A closer look at adaptation mechanisms in simulated environment-driven evolutionary swarm robotics

2013 - 2018
Swarm robotics is a special case within the general field of robotics. The distributed nature makes it...
Dr Andreas Steyven | Director of Studies: Prof Emma Hart | Second Supervisor: Prof Ben Paechter

The evaluation of data filtering criterial in wind turbine power performance assessment

2012 - 2019
Dr Brian Davison | Director of Studies: Prof Tariq Muneer | Second Supervisor: Prof Ahmed Al-Dubai

Novel hyperheuristics applied to the domain of bin packing

2010 - 2014
Hyper-heuristics (HH) have been described as methodologies that aim to offer “good enough -soon enough - cheap enough” solutions to real world...
Dr Kevin Sim | Director of Studies: Prof Emma Hart | Second Supervisor: Prof Ben Paechter

Investigating communicating sequential processes for Java to support ubiquitous computing

2005 - 2009
Ubiquitous Computing promises to enrich our everyday lives by enabling the environment to be enhanced via compu...
Dr Kevin Chalmers | Director of Studies: Prof Jon Kerridge | Second Supervisor: Dr Imed Romdhani

Solving a real world routing proglem using evolutionary algorithms and multi-agent systems

1999 - 2003
Dr Neil Urquhart | Director of Studies: Peter Ross | Second Supervisor: Prof Ben Paechter
16 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 gives invited talk at a Symposium on "Hacking the Immune System"

17 February 2017
This one-day symposium organised at the Radboud University Medical Centre brought together international scientists in the field of tumor immunology, computational and artificial immune systems. Pro...