Biography

I'm research associate at the University of the West of England. Before I came to Bristol, I spent around 4 years in Leeds where I earned a BSc in Computing and MSc in Cognitive Systems. Throughout my BSc and MSc I became especially inspired by the field of biologically-inspired computing - this can be best thought of as observing some facet of nature, forming a working abstraction of a natural process (for example, ant pheremone behaviour), adapting it for use of a computer, and using it to solve problems.

Interests

Running, cycling when I get the chance, football and american football. York City and the New England patriots!

Aside from sports, my non-active interests include swarm behaviour and chaos theory, which I hope to experiment more with in some form or another in the future. I also read a lot; some science/biography, mainly sci-fi and classics. I'm also interested in ancient Greek and Roman culture.

Research

Research Associate

PhD

Specifically, I evolved a population of heavily-abstracted neural structures to function as rules, that solve agent navigation problems in a distributed way. This research has focused on two main points:

• How does the neural model impact the usefulness of the system?
• How does the amount of evolutionary freedom given to these neural rules influence their final structures and learning ability?

Inspiration for this work implicitly owes a lot to Darwinian theories of evolution. For example a "survival of the fittest" pressure is used to keep high-quality individuals in the population whilst killing off individuals that are of little utility. In addition, abstractions of both sexual and asexual reproduction can be seen as a means of breeding and enhancing desirable traits within certain rules.

Motivation can be seen to be the evolution of self-organising learning whereby many of the learning parameters are controlled by the system itself, in response for environmental pressures and interactions.

Member of IEEE CEC review committee

Member of ACM GECCO GA and GBML programme committees

Reviewer for IEEE Transactions on Evolutionary Computing, IEEE Transactions on Circuits and Systems

Presented at the Wrexham Science Festival 2010

Howard, G. D. Taking Inspiration from Nature . on behalf of the University of the West of England (UWE) - videos can be downloaded (36MB .zip file) here.

PhD thesis

Howard, G. D.(2011) A Spiking Neural Learning Classifier System for Continuous Time and Space. University of The West of England

MSc thesis

Howard, G. D.(2006) Visualization of Program Code via Polyhedra . University of Leeds

Journal Articles

Howard, D., Gale, E., Bull, L., De Lacy Costello, B. & Adamatzky, A. (2012) Evolution of Plastic Learning in Spiking Networks via Memristive Connections. IEEE Transactions on Evolutionary Computation (in press).

Conference Proceedings

Howard, D., Bull, L. & Adamatzky, A. (2012) Cartesian Genetic Programming for Memristive Logic Circuits. In Proceedings of the Fifteenth European Conference on Genetic Programming. Springer.

Howard, D., Gale, E., Bull, L., De Lacy Costello, B. & Adamatzky, A. (2011) Evolving Spiking Networks with Variable Memristors. In GECCO-2011: Proceedings of the Genetic and Evolutionary Computation Conference. ACM Press.

also appears as:

Gerard Howard, Ella Gale, Larry Bull, Ben de Lacy Costello & Andy Adamatzky. (2011). Evolving Spiking Networks with Variable Memristors. SIGEVOlution 5, 2 (August 2011), 9-20. DOI=10.1145/2020616.2020618

Howard, D., Gale, E., Bull, L., De Lacy Costello, B. & Adamatzky, A. (2011) Towards Evolving Spiking Networks with Memristive Synapses. In Proceedings of the IEEE Symposium on Artificial Life. IEEE.

Howard, D., Bull, L. & Lanzi, P-L. (2010) Use of a Connection-Selection Scheme in Neural XCSF. In J. Bacardit, et al. (eds) Learning Classifier Systems: Proceedings of the International Workshops IWLCS 2008 and 2009. Springer, pp87-106.

Howard, D., Bull, L. & Lanzi, P-L. (2010) A Spiking Neural Representation for XCSF. In Proceedings of the IEEE Congress on Evolutionary Computation. IEEE Press.

Howard, D., Bull, L. & Lanzi, P-L. (2009) Continuous Actions in Continuous Space and Time using Self-Adaptive Constructivism in Neural XCSF. In GECCO-2009: Proceedings of the Genetic and Evolutionary Computation Conference. ACM Press.

Howard, D., Bull, L. & Lanzi, P-L. (2008) Self-Adaptive Constructivism in Neural XCS and XCSF. In M. Keijzer et al. (eds)GECCO-2008: Proceedings of the Genetic and Evolutionary Computation Conference. ACM Press, pp1389-1396.

Howard, D. & Bull, L. (2008) On the Effects of Node Duplication and Connection-Orientated Constructivism in Neural XCSF. In M. Keijzer et al. (eds)GECCO-2008: Proceedings of the Genetic and Evolutionary Computation Conference. ACM Press, pp1977-1984.

Selected technical reports

Howard, G. D. & Bull, L. (2009) A Spiking Neural Representation for XCSF . UWELCSG09-003

Howard, G. D., Bull, L. & Lanzi, P-L. (2009) Continuous Actions in Continuous Space and Time using Self-Adaptive Constructivism in Neural XCSF . UWELCSG09-002

Howard, G. D., Bull, L. & Lanzi, P-L. (2008) Self-Adaptive Constructivism in Neural XCS and XCSF. UWELCSG08-001

Howard, G. D. & Bull, L. (2008) On the Effects of Node Duplication and Connection-Oriented Constructivism in Neural XCSF. UWELCSG08-003

Contact

email: david4DOThowardATuweDOTacDOTuk