If you want to know more about who I am, my background, or anything else then scroll down!
Who Am I?#
I am Dan, and I am a PhD student at University of York, UK. I am originally from Manchester and that is also where I achieved my Bachelors at MMU. I play basketball and played american football (in the past, not anymore). Here are a few random pictures of me:
My PhD is in safe artificial intelligence with a focus on safe reinforcement learning. I particularly enjoy the challenge of safe exploration in black-box environments, but in general I enjoy a myriad of topics like uncertainty quantification, continual learning, causality, etc.
Papers#
Here are all of my publications, including where they were published. If you want an easy-to-read version that includes small tutorials, see my paper posts.
- Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding ~ arXiv
- Enhancing Fairness in Neural Networks Using FairVIC ~ arXiv
- Robust Uncertainty Quantification using Conformalised Monte Carlo Prediction ~ AAAI ‘24
Reviews#
Here are a list of venues that I have reviewed papers for throughout my career.
2024#
WAISE ‘24 ISSRE ‘24 YISEC ‘24 Nasa Formal Methods ‘24 FormaliSE ‘24
2023#
Education#
Doctor of Philosophy - PhD
2022 - 2026
Computer Science
I am currently studying for my PhD in safe artificial intelligence.
Bachelor of Science - BS (Hons)
2018 - 2022
Computer Science
I graduated with 1st Class Honours from Manchester Metropolitan University.