Skip to main content

Research Repository

Advanced Search

All Outputs (89)

Accelerating neural network architecture search using multi-GPU high-performance computing (2022)
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 particular problem requires experience and tedious trial and error. Automating... Read More about Accelerating neural network architecture search using multi-GPU high-performance computing.

A Cross-Domain Method for Generation of Constructive and Perturbative Heuristics (2021)
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 domain-barrier and are manipulated by the hyper-heuristic itself. However, for... Read More about A Cross-Domain Method for Generation of Constructive and Perturbative Heuristics.

Evolving planar mechanisms for the conceptual stage of mechanical design (2019)
Presentation / Conference Contribution
Lapok, P., Lawson, A., & Paechter, B. (2019, July). Evolving planar mechanisms for the conceptual stage of mechanical design. Presented at GECCO '19, Prague, Czech Republic

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 conceptual design stage of mechanism design which meet their design brief. The... Read More about Evolving planar mechanisms for the conceptual stage of mechanical design.

Improving the performance of a preference-based multi-objective algorithm to optimize food treatment processes (2019)
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, such as the one considered here, the computational cost of evaluating the c... Read More about Improving the performance of a preference-based multi-objective algorithm to optimize food treatment processes.

2-Dimensional Outline Shape Representation for Generative Design with Evolutionary Algorithms (2018)
Presentation / Conference Contribution
Lapok, P., Lawson, A., & Paechter, B. (2018, September). 2-Dimensional Outline Shape Representation for Generative Design with Evolutionary Algorithms. Presented at EngOpt 2018 International Conference on Engineering Optimization, Lisboa, Portugal

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 specific area of mechanical design focuses on planar mechanisms. These are a... Read More about 2-Dimensional Outline Shape Representation for Generative Design with Evolutionary Algorithms.

On the Synthesis of Perturbative Heuristics for Multiple Combinatorial Optimisation Domains (2018)
Presentation / Conference Contribution
Stone, C., Hart, E., & Paechter, B. (2018, September). On the Synthesis of Perturbative Heuristics for Multiple Combinatorial Optimisation Domains. Presented at Fifteenth International Conference on Parallel Problem Solving from Nature (PPSN XV), Coimbra, Portugal

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, there is a lack of available heuristics, while for novel problems, no heur... Read More about On the Synthesis of Perturbative Heuristics for Multiple Combinatorial Optimisation Domains.

Evolution of a Functionally Diverse Swarm via a Novel Decentralised Quality-Diversity Algorithm (2018)
Presentation / Conference Contribution
Hart, E., Steyven, A. S. W., & Paechter, B. (2018, July). Evolution of a Functionally Diverse Swarm via a Novel Decentralised Quality-Diversity Algorithm. Presented at GECCO 2018, Kyoto, Japan

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 range of studies that includes insect groups, human groups and swarm robot... Read More about Evolution of a Functionally Diverse Swarm via a Novel Decentralised Quality-Diversity Algorithm.

Automatic Generation of Constructive Heuristics for Multiple Types of Combinatorial Optimisation Problems with Grammatical Evolution and Geometric Graphs (2018)
Presentation / Conference Contribution
Stone, C., Hart, E., & Paechter, B. (2018, April). Automatic Generation of Constructive Heuristics for Multiple Types of Combinatorial Optimisation Problems with Grammatical Evolution and Geometric Graphs. Presented at 21st International Conference, EvoApplications 2018, Parma, Italy

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 heuristics often suffice in this case. However, for many domains, a simple heurist... Read More about Automatic Generation of Constructive Heuristics for Multiple Types of Combinatorial Optimisation Problems with Grammatical Evolution and Geometric Graphs.

Evaluation of a genetic representation for outline shapes (2017)
Presentation / Conference Contribution
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-world problem of modelling and evolving planar mechanical lever systems. T... Read More about Evaluation of a genetic representation for outline shapes.

On the comparison of initialisation strategies in differential evolution for large scale optimisation (2017)
Journal Article
Segredo, E., Paechter, B., Segura, C., & González-Vila, C. I. (2018). On the comparison of initialisation strategies in differential evolution for large scale optimisation. Optimization Letters, 12(1), 221-234. https://doi.org/10.1007/s11590-017-1107-z

Differential Evolution (DE) has shown to be a promising global opimisation solver for continuous problems, even for those with a large dimensionality. Different previous works have studied the effects that a population initialisation strategy has on... Read More about On the comparison of initialisation strategies in differential evolution for large scale optimisation.

An investigation of environmental influence on the benefits of adaptation mechanisms in evolutionary swarm robotics (2017)
Presentation / Conference Contribution
Steyven, A., Hart, E., & Paechter, B. (2017, July). An investigation of environmental influence on the benefits of adaptation mechanisms in evolutionary swarm robotics. Presented at Genetic and Evolutionary Computation Conference - GECCO '17

A robotic swarm that is required to operate for long periods in a potentially unknown environment can use both evolution and individual learning methods in order to adapt. However, the role played by the environment in influencing the effectiveness o... Read More about An investigation of environmental influence on the benefits of adaptation mechanisms in evolutionary swarm robotics.

Hybridisation of Evolutionary Algorithms through hyper-heuristics for global continuous optimisation (2016)
Presentation / Conference Contribution
Segredo, E., Lalla-Ruiz, E., Hart, E., Paechter, B., & Voß, S. (2016, May). Hybridisation of Evolutionary Algorithms through hyper-heuristics for global continuous optimisation. Presented at Learning and Intelligent OptimizatioN Conference LION 10, Ischia Island (Napoli), Italy

Choosing the correct algorithm to solve a problem still remains an issue 40 years after the Algorithm Selection Problem was first posed. Here we propose a hyper-heuristic which can apply one of two meta-heuristics at the current stage of the search.... Read More about Hybridisation of Evolutionary Algorithms through hyper-heuristics for global continuous optimisation.

Hybrid parameter control approach applied to a diversity-based multi-objective Memetic Algorithm for frequency assignment problems (2016)
Presentation / Conference Contribution
Segredo, E., Paechter, B., Hart, E., & Gonz´alez-Vila, C. I. (2016, July). Hybrid parameter control approach applied to a diversity-based multi-objective Memetic Algorithm for frequency assignment problems. Presented at IEEE World Congress on Computational Intelligence

In order to address the difficult issue of parameter setting within a diversity-based Multi-objective Evolutionary Algorithm (MOEA), we recently proposed a hybrid control scheme based on both Fuzzy Logic Controllers (FLCs) and Hyper-heuristics (HHs).... Read More about Hybrid parameter control approach applied to a diversity-based multi-objective Memetic Algorithm for frequency assignment problems.

Trickle-Plus: Elastic Trickle algorithm for Low-power networks and Internet of Things (2016)
Presentation / Conference Contribution
Ghaleb, B., Al-Dubai, A., Ekonomou, E., Paechter, B., & Qasem, M. (2016, April). Trickle-Plus: Elastic Trickle algorithm for Low-power networks and Internet of Things. Presented at 2016 IEEE Wireless Communications and Networking Conference

Constrained Low-power and Lossy networks (LLNs) represent the building block for the ever-growing Internet of Things (IoT) that deploy the Routing Protocol for Low Power and Lossy networks (RPL) as a key routing standard. RPL, along with other routin... Read More about Trickle-Plus: Elastic Trickle algorithm for Low-power networks and Internet of Things.

Analysing the performance of migrating birds optimisation approaches for large scale continuous problems (2016)
Presentation / Conference Contribution
Lalla-Ruiz, E., Segredo, E., Voss, S., Hart, E., & Paechter, B. (2016, September). Analysing the performance of migrating birds optimisation approaches for large scale continuous problems. Presented at 14th International Conference on Parallel Problem Solving from Nature (PPSN 2016)

We present novel algorithmic schemes for dealing with large scale continuous problems. They are based on the recently proposed population-based meta-heuristics Migrating Birds Optimisation (mbo) and Multi-leader Migrating Birds Optimisation (mmbo), t... Read More about Analysing the performance of migrating birds optimisation approaches for large scale continuous problems.

Understanding Environmental Influence in an Open-Ended Evolutionary Algorithm (2016)
Presentation / Conference Contribution
Steyven, A., Hart, E., & Paechter, B. (2016, October). Understanding Environmental Influence in an Open-Ended Evolutionary Algorithm. Presented at PPSN 2016 14th International Conference on Parallel Problem Solving from Nature

It is well known that in open-ended evolution, the nature of the environment plays in key role in directing evolution. However, in Evolutionary Robotics, it is often unclear exactly how parameterisation of a given environment might influence the emer... Read More about Understanding Environmental Influence in an Open-Ended Evolutionary Algorithm.

Improving survivability in environment-driven distributed evolutionary algorithms through explicit relative fitness and fitness proportionate communication. (2015)
Presentation / Conference Contribution
Hart, E., Steyven, A., & Paechter, B. (2015, July). Improving survivability in environment-driven distributed evolutionary algorithms through explicit relative fitness and fitness proportionate communication. Presented at Proceedings of the 2015 on Genetic and Evolutionary Computation Conference - GECCO '15

Ensuring the integrity of a robot swarm in terms of maintaining a stable population of functioning robots over long periods of time is a mandatory prerequisite for building more complex systems that achieve user-defined tasks. mEDEA is an environ... Read More about Improving survivability in environment-driven distributed evolutionary algorithms through explicit relative fitness and fitness proportionate communication..

The Cost of Communication: Environmental Pressure and Survivability in mEDEA (2015)
Presentation / Conference Contribution
Steyven, A., Hart, E., & Paechter, B. (2015, July). The Cost of Communication: Environmental Pressure and Survivability in mEDEA. Presented at GECCO ’15

We augment the mEDEA algorithm to explicitly account for the costs of communication between robots. Experimental results show that adding a costs for communication exerts environmental pressure to implicitly select for genomes that maintain high... Read More about The Cost of Communication: Environmental Pressure and Survivability in mEDEA.

A Lifelong Learning Hyper-heuristic Method for Bin Packing (2015)
Journal Article
Hart, E., Sim, K., & Paechter, B. (2015). A Lifelong Learning Hyper-heuristic Method for Bin Packing. Evolutionary Computation, 23(1), 37-67. https://doi.org/10.1162/EVCO_a_00121

We describe a novel Hyper-heuristic system which continuously learns over time to solve a combinatorial optimisation problem. The system continuously generates new heuristics and samples problems from its environment; representative problems and heur... Read More about A Lifelong Learning Hyper-heuristic Method for Bin Packing.

Learning to solve bin packing problems with an immune inspired hyper-heuristic. (2013)
Presentation / Conference Contribution
Sim, K., Hart, E., & Paechter, B. (2013, September). Learning to solve bin packing problems with an immune inspired hyper-heuristic

Motivated by the natural immune system's ability to defend the body by generating and maintaining a repertoire of antibodies that collectively cover the potential pathogen space, we describe an artificial system that discovers and maintains a reperto... Read More about Learning to solve bin packing problems with an immune inspired hyper-heuristic..