All Outputs (8)

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.

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.

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.

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.

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.

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.

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.