Our Team > Our PhD Students > Colin Roitt

Colin Roitt

Our PhD Students

University of York

Colin graduated with a bachelor’s degree in Computer Science in 2019 and then, in the same year, made the move to the University of York to pursue a Master’s in Advanced Computer Science. Graduating a year later, they went on to work as a front-end and product developer for Cambridge-base cyber security company Darktrace.

They have a keen interest in Artificial Intelligence – specifically evolutionary algorithms – and are driven by novel approaches and applications of AI. The biologically inspired solutions of RIED were one of the main draws of the project for them and something they hope to carry forward into the future alongside other novel approaches to AI.

RIED Specific Links & Papers

  • Enough is Enough: Learning to Stop in Generative Systems

    Colin Roitt et al

    We are delighted to share that Colin Roitt, a RIED PhD Student at the University of York, recently presented a paper and poster at the 13th International Conference on Artificial Intelligence in Music, Sound, Art and Design (EvoMUSART). This was part of “evostar”, the leading European event on Bio-Inspired Computation that took part in Aberystwyth, Wales, UK 3-5 April

    Colin’s paper entitled “Enough is Enough: Learning to Stop in Generative Systems” proposed that while Gene regulatory networks (GRNs) have been used to drive artificial generative systems these systems must begin and then stop generation, or growth, akin to their biological counterpart. A Long Short-Term Memory style network was implemented as a GRN for an Evo-Devo generative system and was tested on one simple (single point target) and two more complex problems (structured and unstructured point clouds). The novel LSTMGRN performed well in simple tasks to optimise stopping conditions, but struggled to manage more complex environments. This early work in self-regulating growth will allow for further research in more complex systems to allow the removal of hyperparameters and allowing the evolutionary system to stop dynamically and prevent organisms overshooting the optimal.

    Here are links to the paper

    https://link.springer.com/chapter/10.1007/978-3-031-56992-0_22

    https://doi.org/10.1007/978-3-031-56992-0_22

    Well done Colin !

View