Algorithm selection using deep learning without feature extraction (2019)
Presentation / Conference Contribution
Alissa, M., Sim, K., & Hart, E. (2019, July). Algorithm selection using deep learning without feature extraction. Presented at Genetic and Evolutionary Computing Conference (GECCO) 2019, Prague, Czech Republic

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.

General and craniofacial development are complex adaptive processes influenced by diversity (2014)
Journal Article
Hart, E., Brook, A. H., Brook-O'Donnell, M., Hone, A., Hughes, T., & Smith, R. (2014). General and craniofacial development are complex adaptive processes influenced by diversity. Australian Dental Journal, 59(S1), 13-22. https://doi.org/10.1111/adj.12158

Complex systems are present in such diverse areas as social systems, economies, ecosystems and Biology and, therefore, are highly relevant to dental research, education and practice. A Complex Adaptive System in biological development is a dynamic pr... Read More about General and craniofacial development are complex adaptive processes influenced by diversity.

A Hyper-Heuristic classifier for one dimensional bin packing problems: Improving classification accuracy by attribute evolution. (2012)
Presentation / Conference Contribution
Sim, K., Hart, E., & Paechter, B. (2012, September). A Hyper-Heuristic classifier for one dimensional bin packing problems: Improving classification accuracy by attribute evolution. Presented at International Conference on Parallel Problem Solving from Nature

A hyper-heuristic for the one dimensional bin packing problem is presented that uses an Evolutionary Algorithm (EA) to evolve a set of attributes that characterise a problem instance. The EA evolves divisions of variable quantity and dimension that r... Read More about A Hyper-Heuristic classifier for one dimensional bin packing problems: Improving classification accuracy by attribute evolution..

Evolutionary scheduling: a review. (2005)
Journal Article
Hart, E., Ross, P., & Corne, D. (2005). Evolutionary scheduling: a review. Genetic Programming and Evolvable Machines, 6, 191-220. https://doi.org/10.1007/s10710-005-7580-7

Early and seminal work which applied evolutionary computing methods to scheduling problems from 1985 onwards laid a strong and exciting foundation for the work which has been reported over the past decade or so. A survey of the current state-of-the-a... Read More about Evolutionary scheduling: a review..

The impact of the shape of antibody recognition regions on the emergence of idiotypic networks. (2005)
Journal Article
Hart, E., & Ross, P. (2005). The impact of the shape of antibody recognition regions on the emergence of idiotypic networks. International Journal of Unconventional Computing, 1, 281-313

One of the components of an AIS algorithm that most distinguishes it from other paradigms is the use of an affinity funciton. However, for the most part, the implications of choosing a suitable matching rule and the likely effects on the algorithm fr... Read More about The impact of the shape of antibody recognition regions on the emergence of idiotypic networks..

Exploiting the analogy between the immune system and sparse distributed memory. (2003)
Journal Article
Hart, E., & Ross, P. (2003). Exploiting the analogy between the immune system and sparse distributed memory. Genetic Programming and Evolvable Machines, 4(4), 333-358. https://doi.org/10.1023/a%3A1026191011609

The relationship between immunological memory and a class of associative memories known as sparse distributed memories (SDM) is well known. This paper proposes a new model for clustering non-stationary data based on a combination of salient features... Read More about Exploiting the analogy between the immune system and sparse distributed memory..

A role for immunology in 'next generation' robots. (2003)
Presentation / Conference Contribution
Hart, E., Ross, P., Webb, A., & Lawson, A. (2003, September). A role for immunology in 'next generation' robots. Presented at Second International Conference, ICARIS 2003, Edinburgh, UK, September 1-3, 2003, Proceedings: volume 2787 of Lecture Notes on Computer Science: Artificial Immune Systems, Editors: Timmis, J., Bentley, P. and Hart, E., Springer, ISBN: 978-3-540-40766-9

Much of current robot research is about learning tasks in which the task to be achieved is pre-specified, a suitable technology for the task is chosen and the learning process is experimentally investigated. A more interesting research question is ho... Read More about A role for immunology in 'next generation' robots..

Controlling a simulated Khepera with an XCS classifier system with memory. (2003)
Presentation / Conference Contribution
Webb, A., Hart, E., Ross, P., & Lawson, A. (2003, September). Controlling a simulated Khepera with an XCS classifier system with memory. Presented at 7th European Conference on Artificial Life, ECAL 2003: Advances in Artificial Life

Autonomous agents commonly suffer from perceptual aliasing in which differing situations are perceived as identical by the robots sensors, yet require different courses of action. One technique for addressing this problem is to use additional interna... Read More about Controlling a simulated Khepera with an XCS classifier system with memory..

Requirements for getting a robot to grow up. (2003)
Presentation / Conference Contribution
Ross, P., Hart, E., Lawson, A., Webb, A., Prem, E., Poelz, P., & Morgavi, G. (2003, September). Requirements for getting a robot to grow up. Presented at 7th European Conference on Artificial Life, ECAL 2003: Advances in Artificial Life

Learning a procedure that can solve hard bin-packing problems: a new GA-based approach to hyperheuristics. (2003)
Presentation / Conference Contribution
Ross, P., Marin-Blazquez, J. G., Schulenburg, S., & Hart, E. (2003, July). Learning a procedure that can solve hard bin-packing problems: a new GA-based approach to hyperheuristics. Presented at Genetic and Evolutionary Computation Conference (GECCO) 2003

The idea underlying hyper-heuristics is to discover some
combination of familiar, straightforward heuristics that performs very well across a whole range of problems. To be worthwhile, such a combination should outperform all of the constituent heur... Read More about Learning a procedure that can solve hard bin-packing problems: a new GA-based approach to hyperheuristics..

Hyper-heuristics: learning to combine simple heuristics in bin-packing problems. (2002)
Presentation / Conference Contribution
Ross, P., Schulenburg, S., Marin-Blazquez, J. G., & Hart, E. (2002, July). Hyper-heuristics: learning to combine simple heuristics in bin-packing problems. Presented at Genetic and Evolutionary Computation Conference (GECCO)

Evolutionary algorithms (EAs) often appear to be a ‘black box’, neither offering worst-case bounds nor any guarantee of optimality when used to solve individual problems. They can also take much longer than non-evolutionary methods. We
try to addres... Read More about Hyper-heuristics: learning to combine simple heuristics in bin-packing problems..

Improving street based routing using building block mutations. (2002)
Presentation / Conference Contribution
Urquhart, N. B., Ross, P., Paechter, B., & Chisholm, K. (2002, April). Improving street based routing using building block mutations. Presented at Workshops on Applications of Evolutionary Computation EvoWorkshops 2002, Kinsale, Ireland

Street based routing (SBR) is a real-world inspired routing problem that builds routes within an urban area for mail deliveries. The authors have previously attempted to solve this problem using an Evolutionary Algorithm (EA). In this paper the autho... Read More about Improving street based routing using building block mutations..

Street-based routing using an evolutionary algorithm (2001)
Presentation / Conference Contribution
Urquhart, N. B., Paechter, B., & Chisholm, K. (2001, April). Street-based routing using an evolutionary algorithm. Presented at Workshops on Applications of Evolutionary Computation EvoWorkshops 2001, Como, Italy

Much research has been carried out into solving routing problems using both Evolutionary Techniques and other methods. In this paper the authors investigate the usage of an Evolutionary Algorithms to solve the Street-Based Routing Problem (SBRP). The... Read More about Street-based routing using an evolutionary algorithm.

Optimising an evolutionary algorithm for scheduling (2000)
Presentation / Conference Contribution
Urquhart, N. B., Chisholm, K., & Paechter, B. (2000, April). Optimising an evolutionary algorithm for scheduling. Presented at EvoWorkshops 2000: EvoIASP, EvoSCONDI, EvoTel, EvoSTIM, EvoRob, and EvoFlight,, Edinburgh

This paper examines two techniques for setting the parameters of an evolutionary Algorithm (EA). The example EA used for test purposes undertakes a simple scheduling problem. An initial version of the EA was tested utilising a set of parameters that... Read More about Optimising an evolutionary algorithm for scheduling.