Algorithms for AI inspired by the bounded rationality of humans at University of Bath on FindAPhD.com

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities

Dr Özgür Şimşek No more applications being accepted Self-Funded PhD Students Only

Bath United Kingdom Applied Mathematics Artificial Intelligence Data Analysis Machine Learning Economics Software Engineering Statistics

About the Project

This project will develop new algorithms for AI inspired by the bounded rationality of humans, in other words, by how people are able to make good decisions when they have limited time, information, and computation in environments that are complex, dynamic, and deeply uncertain. In contrast, today’s AI algorithms generally require extensive time, information, and computation and are effective in environments that are highly confined, stable, and predictable. Advances in the speed of computation will continue to extend the capabilities of our AI systems. But computational speed can take us only so far. For fundamental shifts in the capabilities of our AI systems, we need fundamentally new ideas in our learning algorithms.

This project will use as a foundation the large, interdisciplinary scientific literature on bounded rationality. In designing boundedly-rational AI algorithms, it will pay particular attention to the fit between “the computational capacities of the actor and the structure of the environment,” as noted by Herbert Simon. Algorithmic focus will be on reinforcement learning and supervised learning. The algorithmic approaches explored will depend on the background and interests of the student. The objective is to improve the state-of-the art in both accuracy (and similar metrics) and explainability. The project will be supervised by Dr Özgür Şimşek at the Department of Computer Science at the University of Bath. Examples of earlier work by the PI are listed in the references.

The University of Bath is located in the UNESCO World Heritage city of Bath, providing a vibrant research environment in one of the most beautiful areas in the UK.

Informal enquires are welcome and should be directed to Dr Özgür Şimşek ([Email Address Removed]).

Applicants should hold, or expect to receive, a First or Upper Second Class Honours degree. A master’s level qualification would also be advantageous. Desirable qualities in candidates include intellectual curiosity, a strong background in mathematics and programming experience.

Formal applications should be accompanied by a research proposal and made via the University of Bath’s online application form. Further information about the application process can be found here.

Start date: Between 8 January and 30 September 2024.

Funding Notes

We welcome applications from candidates who can source their own funding. Tuition fees for the 2023/4 academic year are £4,700 (full-time) for Home students and £26,600 (full-time) for International students. For information about eligibility for Home fee status: https://www.bath.ac.uk/guides/understanding-your-tuition-fee-status/.

References

[1] K. Katsikopoulos, Ö. Şimşek, M. Buckmann, and G. Gigerenzer (In press). Classification in the wild: The science and art of transparent decision making. MIT Press, Cambridge, MA.
[2] M. J. Lichtenberg and Ö. Şimşek (2019). Regularization in directable environments with application toTetris. International Conference on Machine Learning (ICML).
[3] Ö. Şimşek, S. Algórta, and A. Kothiyal (2016). Why most decisions are easy in Tetris—and perhaps in other sequential decision problems, as well. International Conference on Machine Learning (ICML).
[4] Ö. Şimşek and D. Jensen (2008). Navigating networks by using homophily and degree. Proceedings of the National Academy of Sciences of the USA (PNAS), 105(35):12758–12762.