Ben Paechter
Ben Paechter

Prof Ben Paechter FBCS CITP

Professor

Biography

Prof. Ben Paechter is Director of Research in the School of Computing. He was Coordinator of the EvoNet, PerAda, and AWARE Coordination Actions within Future and Emerging Technologies (FET) and Deputy Coordinator of the FOCAS Coordination Action. He was a Principal Investigator of the “Speckled Computing” consortium of Scottish universities developing “spray on” computers for wireless sensor networks. He coordinated the FET DREAM project looking at peer-to-peer distribution evolution. He was the scientific officer in charge of the Metaheuristics Network examining the use of metaheuristics for combinatorial optimisation and the FET NEWTIES project which created an artificial society and examined the relationships between individual, social, and evolutionary learning. Prof Paechter is an Associate Editor of “Evolutionary Computation” (MIT Press). He was Joint General Chair of Parallel Problem Solving from Nature (PPSN) 2016.

News

Esteem

Editorial Activity

  • Associate Editor of Evolutionary Computation (MIT Press)

 

Media Activity

  • Timetabling software developed within the Centre for Emergent Computing highlighted in new TEDx talk on Evolutionary Computing and Design
  • PerAda team run successful public engagement event at the Science Museum, London
  • IIDI's AWARE project host successful talk at Edinburgh International Science Festival
  • FoCAS Book: Adaptive Collective Systems - Herding Black Sheep

 

Date


92 results

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...

Accelerating neural network architecture search using multi-GPU high-performance computing

Journal Article
Lupión, M., Cruz, N. C., Sanjuan, J. F., Paechter, B., & Ortigosa, P. M. (2023)
Accelerating neural network architecture search using multi-GPU high-performance computing. Journal of Supercomputing, 79, 7609-7625. https://doi.org/10.1007/s11227-022-04960-z
Neural networks stand out from artificial intelligence because they can complete challenging tasks, such as image classification. However, designing a neural network for a par...

A Cross-Domain Method for Generation of Constructive and Perturbative Heuristics

Book Chapter
Stone, C., Hart, E., & Paechter, B. (2021)
A Cross-Domain Method for Generation of Constructive and Perturbative Heuristics. In N. Pillay, & R. Qu (Eds.), Automated Design of Machine Learning and Search Algorithms (91-107). Springer. https://doi.org/10.1007/978-3-030-72069-8_6
Hyper-heuristic frameworks, although intended to be cross-domain at the highest level, usually rely on a set of domain-specific low-level heuristics which exist below the doma...

Evolving planar mechanisms for the conceptual stage of mechanical design

Conference Proceeding
Lapok, P., Lawson, A., & Paechter, B. (2019)
Evolving planar mechanisms for the conceptual stage of mechanical design. In GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference Companion. , (383-384). https://doi.org/10.1145/3319619.3322006
This study presents a method to evolve planar mechanism prototypes using an evolutionary computing approach. Ultimately, the idea is to provide drafts for designers at the con...

Improving the performance of a preference-based multi-objective algorithm to optimize food treatment processes

Journal Article
Ferrández, M. R., Redondo, J. L., Ivorra, B., Ramos, A. M., Ortigosa, P. M., & Paechter, B. (2020)
Improving the performance of a preference-based multi-objective algorithm to optimize food treatment processes. Engineering Optimization, 52(5), 896-913. https://doi.org/10.1080/0305215x.2019.1618289
This work focuses on the optimization of some high-pressure and temperature food treatments. In some cases, when dealing with real-life multi-objective optimization problems, ...

2-Dimensional Outline Shape Representation for Generative Design with Evolutionary Algorithms

Conference Proceeding
Lapok, P., Lawson, A., & Paechter, B. (2019)
2-Dimensional Outline Shape Representation for Generative Design with Evolutionary Algorithms. In H. Rodrigues, J. Herskovits, C. Mota Soares, A. Araújo, J. Guedes, J. Folgado, …J. Madeira (Eds.), EngOpt 2018 Proceedings of the 6th International Conference on Engineering Optimization, (926-937). https://doi.org/10.1007/978-3-319-97773-7_80
In this paper, we investigate the ability of genetic representation methods to describe two-dimensional outline shapes, in order to use them in a generative design system. A s...

On the Synthesis of Perturbative Heuristics for Multiple Combinatorial Optimisation Domains

Conference Proceeding
Stone, C., Hart, E., & Paechter, B. (2018)
On the Synthesis of Perturbative Heuristics for Multiple Combinatorial Optimisation Domains. In Parallel Problem Solving from Nature – PPSN XV 15th International Conference, Coimbra, Portugal, September 8–12, 2018, Proceedings, Part Ihttps://doi.org/10.1007/978-3-319-99253-2_14
Hyper-heuristic frameworks, although intended to be cross-domain at the highest level, rely on a set of domain-specific low-level heuristics at lower levels. For some domains,...

Evolution of a Functionally Diverse Swarm via a Novel Decentralised Quality-Diversity Algorithm

Conference Proceeding
Hart, E., Steyven, A. S. W., & Paechter, B. (2018)
Evolution of a Functionally Diverse Swarm via a Novel Decentralised Quality-Diversity Algorithm. In GECCO '18 Proceedings of the Genetic and Evolutionary Computation Conference, (101-108). https://doi.org/10.1145/3205455.3205481
The presence of functionality diversity within a group has been demonstrated to lead to greater robustness, higher performance and increased problem-solving ability in a broad...

Automatic Generation of Constructive Heuristics for Multiple Types of Combinatorial Optimisation Problems with Grammatical Evolution and Geometric Graphs

Conference Proceeding
Stone, C., Hart, E., & Paechter, B. (2017)
Automatic Generation of Constructive Heuristics for Multiple Types of Combinatorial Optimisation Problems with Grammatical Evolution and Geometric Graphs. In Applications of Evolutionary Computation, 578-593
In many industrial problem domains, when faced with a combinatorial optimisation problem, a “good enough, quick enough” solution to a problem is often required. Simple heurist...

Evaluation of a genetic representation for outline shapes

Conference Proceeding
Lapok, P., Lawson, A., & Paechter, B. (2017)
Evaluation of a genetic representation for outline shapes. In GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion, (1419-1422). https://doi.org/10.1145/3067695.3082501
This work in progress focuses on the evaluation of a genetic representation for outline shapes for planar mechanical levers which addresses the first stage of the complex real...

Current Post Grad projects

Previous Post Grad projects