All Outputs (100)

A Novelty-Search Approach to Filling an Instance-Space with Diverse and Discriminatory Instances for the Knapsack Problem (2022)
Presentation / Conference Contribution
Marrero, A., Segredo, E., León, C., & Hart, E. (2022, September). A Novelty-Search Approach to Filling an Instance-Space with Diverse and Discriminatory Instances for the Knapsack Problem. Presented at Parallel Problem Solving from Nature – PPSN XVII, 17th International Conference, Dortmund, Germany

We propose a new approach to generating synthetic instances in the knapsack domain in order to fill an instance-space. The method uses a novelty-search algorithm to search for instances that are diverse with respect to a feature-space but also elicit... Read More about A Novelty-Search Approach to Filling an Instance-Space with Diverse and Discriminatory Instances for the Knapsack Problem.

Evolutionary Approaches to Improving the Layouts of Instance-Spaces (2022)
Presentation / Conference Contribution
Sim, K., & Hart, E. (2022, September). Evolutionary Approaches to Improving the Layouts of Instance-Spaces. Presented at 17th International Conference, PPSN 2022, Dortmund, Germany

We propose two new methods for evolving the layout of an instance-space. Specifically we design three different fitness metrics that seek to: (i) reward layouts which place instances won by the same solver close in the space; (ii) reward layouts that... Read More about Evolutionary Approaches to Improving the Layouts of Instance-Spaces.

Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers (2022)
Presentation / Conference Contribution
Cardoso, R. P., Hart, E., Burth Kurka, D., & Pitt, J. (2022, April). Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers. Presented at EvoSTAR, Madrid

Using Neuroevolution combined with Novelty Search to promote behavioural diversity is capable of constructing high-performing ensembles for classification. However, using gradient descent to train evolved architectures during the search can be comput... Read More about Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers.

A Neural Approach to Generation of Constructive Heuristics (2021)
Presentation / Conference Contribution
Alissa, M., Sim, K., & Hart, E. (2021, June). A Neural Approach to Generation of Constructive Heuristics. Presented at IEEE Congress on Evolutionary Computation 2021, Kraków, Poland (online)

Both algorithm-selection methods and hyper-heuristic methods rely on a pool of complementary heuristics. Improving the pool with new heuristics can improve performance, however, designing new heuristics can be challenging. Methods such as genetic pro... Read More about A Neural Approach to Generation of Constructive Heuristics.

On the challenges of jointly optimising robot morphology and control using a hierarchical optimisation scheme (2021)
Presentation / Conference Contribution
Goff, L. K. L., & Hart, E. (2021, July). On the challenges of jointly optimising robot morphology and control using a hierarchical optimisation scheme. Presented at GECCO '21: Genetic and Evolutionary Computation Conference, Lille, France

We investigate a hierarchical scheme for the joint optimisation of robot bodies and controllers in a complex morphological space. An evolutionary algorithm optimises body-plans while a separate learning algorithm is applied to each body generated to... Read More about On the challenges of jointly optimising robot morphology and control using a hierarchical optimisation scheme.

Using novelty search to explicitly create diversity in ensembles of classifiers (2021)
Presentation / Conference Contribution
Cardoso, R. P., Hart, E., Kurka, D. B., & Pitt, J. V. (2021, July). Using novelty search to explicitly create diversity in ensembles of classifiers. Presented at GECCO '21: Genetic and Evolutionary Computation Conference, Lille, France [Online]

The diversity between individual learners in an ensemble is known to influence its performance. However, there is no standard agreement on how diversity should be defined, and thus how to exploit it to construct a high-performing classifier. We propo... Read More about Using novelty search to explicitly create diversity in ensembles of classifiers.

WILDA: Wide Learning of Diverse Architectures for Classification of Large Datasets (2021)
Presentation / Conference Contribution
Pitt, J., Burth Kurka, D., Hart, E., & Cardoso, R. P. (2021, April). WILDA: Wide Learning of Diverse Architectures for Classification of Large Datasets. Presented at 24th European Conference, EvoApplications 2021, Online

In order to address scalability issues, which can be a challenge for Deep Learning methods, we propose Wide Learning of Diverse Architectures-a model that scales horizontally rather than vertically, enabling distributed learning. We propose a distrib... Read More about WILDA: Wide Learning of Diverse Architectures for Classification of Large Datasets.

Automated, Explainable Rule Extraction from MAP-Elites archives (2021)
Presentation / Conference Contribution
Urquhart, N., Höhl, S., & Hart, E. (2021, April). Automated, Explainable Rule Extraction from MAP-Elites archives. Presented at EvoAPPs2021, Online

Quality-diversity(QD) algorithms that return a large archive of elite solutions to a problem provide insights into how high-performing solutions are distributed throughout a feature-space defined by a user — they are often described as illuminating t... Read More about Automated, Explainable Rule Extraction from MAP-Elites archives.

Improving the Naturalness and Diversity of Referring Expression Generation models using Minimum Risk Training (2020)
Presentation / Conference Contribution
Panagiaris, N., Hart, E., & Gkatzia, D. (2020, December). Improving the Naturalness and Diversity of Referring Expression Generation models using Minimum Risk Training. Presented at International Conference on Natural Language Generation (INLG 2020), Dublin, Ireland

In this paper we consider the problem of optimizing neural Referring Expression Generation (REG) models with sequence level objectives. Recently reinforcement learning (RL) techniques have been adopted to train deep end-to-end systems to directly opt... Read More about Improving the Naturalness and Diversity of Referring Expression Generation models using Minimum Risk Training.

Hardware Design for Autonomous Robot Evolution (2020)
Presentation / Conference Contribution
Hale, M. F., Angus, M., Buchanan, E., Li, W., Woolley, R., Le Goff, L. K., De Carlo, M., Timmis, J., Winfield, A. F., Hart, E., Eiben, A. E., & Tyrrell, A. M. (2020, December). Hardware Design for Autonomous Robot Evolution. Presented at International Conference on Evolvable Hardware, Canberra Australia

The long term goal of the Autonomous Robot Evolution (ARE) project is to create populations of physical robots, in which both the controllers and body plans are evolved. The transition for evolutionary designs from purely simulation environments into... Read More about Hardware Design for Autonomous Robot Evolution.

Evolution of Diverse, Manufacturable Robot Body Plans (2020)
Presentation / Conference Contribution
Buchanan, E., Le Goff, L., Hart, E., Eiben, A. E., De Carlo, M., Li, W., Hale, M. F., Angus, M., Woolley, R., Winfield, A. F., Timmis, J., & Tyrrell, A. M. (2020, December). Evolution of Diverse, Manufacturable Robot Body Plans. Presented at International Conference on Evolvable Systems (ICES), Canberra, Australia

Advances in rapid prototyping have opened up new avenues of research within Evolutionary Robotics in which not only controllers but also the body plans (morphologies) of robots can evolve in real-time and real-space. However, this also introduces new... Read More about Evolution of Diverse, Manufacturable Robot Body Plans.

Improving Classification of Metamorphic Malware by Augmenting Training Data with a Diverse Set of Evolved Mutant Samples (2020)
Presentation / Conference Contribution
Babaagba, K., Tan, Z., & Hart, E. (2020, July). Improving Classification of Metamorphic Malware by Augmenting Training Data with a Diverse Set of Evolved Mutant Samples. Presented at The 2020 IEEE Congress on Evolutionary Computation (IEEE CEC 2020), Glasgow, UK

Detecting metamorphic malware provides a challenge to machine-learning models as trained models might not generalise to future mutant variants of the malware. To address this, we explore whether machine-learning models can be improved by augmenting t... Read More about Improving Classification of Metamorphic Malware by Augmenting Training Data with a Diverse Set of Evolved Mutant Samples.

Sample and time efficient policy learning with CMA-ES and Bayesian Optimisation (2020)
Presentation / Conference Contribution
Le Goff, L. K., Buchanan, E., Hart, E., Eiben, A. E., Li, W., De Carlo, M., Hale, M. F., Angus, M., Woolley, R., Timmis, J., Winfield, A., & Tyrrell, A. M. (2020, July). Sample and time efficient policy learning with CMA-ES and Bayesian Optimisation. Presented at ALife 2020, Online

In evolutionary robot systems where morphologies and controllers of real robots are simultaneously evolved, it is clear that there is likely to be requirements to refine the inherited controller of a 'newborn' robot in order to better align it to its... Read More about Sample and time efficient policy learning with CMA-ES and Bayesian Optimisation.

On Pros and Cons of Evolving Topologies with Novelty Search (2020)
Presentation / Conference Contribution
Le Goff, L. K., Hart, E., Coninx, A., & Doncieux, S. (2020). On Pros and Cons of Evolving Topologies with Novelty Search. In ALIFE 2020: The 2020 Conference on Artificial Life (423-431). https://doi.org/10.1162/isal_a_00291

Novelty search was proposed as a means of circumventing deception and providing selective pressure towards novel behaviours to provide a path towards open-ended evolution. Initial implementations relied on neuro-evolution approaches which increased n... Read More about On Pros and Cons of Evolving Topologies with Novelty Search.

A Deep Learning Approach to Predicting Solutions in Streaming Optimisation Domains (2020)
Presentation / Conference Contribution
Alissa, M., Sim, K., & Hart, E. (2020, July). A Deep Learning Approach to Predicting Solutions in Streaming Optimisation Domains. Presented at GECCO ’20, Cancún, Mexico

In the field of combinatorial optimisation, per-instance algorithm selection still remains a challenging problem, particularly with respect to streaming problems such as packing or scheduling. Typical approaches involve training a model to predict th... Read More about A Deep Learning Approach to Predicting Solutions in Streaming Optimisation Domains.

Automatic Generation of Adversarial Metamorphic Malware Using MAP-Elites (2020)
Presentation / Conference Contribution
Babaagba, K. O., Tan, Z., & Hart, E. (2020, April). Automatic Generation of Adversarial Metamorphic Malware Using MAP-Elites. Presented at EvoStar 2020, Seville, Spain

In the field of metamorphic malware detection, training a detection model with malware samples that reflect potential mutants of the malware is crucial in developing a model resistant to future attacks. In this paper, we use a Multi-dimensional Archi... Read More about Automatic Generation of Adversarial Metamorphic Malware Using MAP-Elites.

Nowhere Metamorphic Malware Can Hide - A Biological Evolution Inspired Detection Scheme (2019)
Presentation / Conference Contribution
Babaagba, K. O., Tan, Z., & Hart, E. (2019, November). Nowhere Metamorphic Malware Can Hide - A Biological Evolution Inspired Detection Scheme. Presented at The 5th International Conference on Dependability in Sensor, Cloud, and Big Data Systems and Applications (DependSys 2019), Guangzhou, China

The ability to detect metamorphic malware has generated significant research interest over recent years, particularly given its proliferation on mobile devices. Such malware is particularly hard to detect via signature-based intrusion detection syste... Read More about Nowhere Metamorphic Malware Can Hide - A Biological Evolution Inspired Detection Scheme.

The ARE Robot Fabricator: How to (Re)produce Robots that Can Evolve in the Real World (2019)
Presentation / Conference Contribution
Hale, M. F., Buchanan, E., Winfield, A. F., Timmis, J., Hart, E., Eiben, A. E., Angus, M., Veenstra, F., Li, W., Woolley, R., De Carlo, M., & Tyrrell, A. M. (2019, July). The ARE Robot Fabricator: How to (Re)produce Robots that Can Evolve in the Real World. Presented at Artificial Life, Newcastle, UK

The long term vision of the Autonomous Robot Evolution (ARE) project is to create an ecosystem of both virtual and physical robots with evolving brains and bodies. One of the major challenges for such a vision is the need to construct many unique ind... Read More about The ARE Robot Fabricator: How to (Re)produce Robots that Can Evolve in the Real World.

Being a leader or being the leader: The evolution of institutionalised hierarchy (2019)
Presentation / Conference Contribution
Perret, C., Hart, E., & Powers, S. T. (2019, July). Being a leader or being the leader: The evolution of institutionalised hierarchy. Presented at ALIFE 2019, Newcastle upon Tyne

Human social hierarchy has the unique characteristic of existing in two forms. Firstly, as an informal hierarchy where leaders and followers are implicitly defined by their personal characteristics, and secondly, as an institutional hierarchy where l... Read More about Being a leader or being the leader: The evolution of institutionalised hierarchy.

Algorithm selection using deep learning without feature extraction (2019)
Presentation / Conference Contribution
Alissa, M., Sim, K., & Hart, E. (2019). Algorithm selection using deep learning without feature extraction. In GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference Companion (198-206). https://doi.org/10.1145/3321707.3321845

We propose a novel technique for algorithm-selection which adopts a deep-learning approach, specifically a Recurrent-Neural Network with Long-Short-Term-Memory (RNN-LSTM). In contrast to the majority of work in algorithm-selection, the approach does... Read More about Algorithm selection using deep learning without feature extraction.