Mr Lachlan Simpson
Higher Degree by Research Candidate
School of Electrical and Mechanical Engineering
College of Engineering and Information Technology
My research leverages tools from differential geometry and Lie theory to develop robust and user-friendly explainable AI models. I also work in developing physics-informed neural networks (PINNs) for problems in wave physics. In particular, I have applied PINNs to quantum graphs to engineer desirable properties of lattices.
| Date | Institution name | Country | Title |
|---|---|---|---|
| University of Adelaide | Australia | Bachelor of Computer and Mathematical Sciences | |
| University of Adelaide | Australia | Honours Bachelor of Computer and Mathematical Sciences (Pure Mathematics) |
| Year | Citation |
|---|---|
| 2026 | Simpson, L., Millar, K., Cheng, A., Lim, C. C., & Chew, H. G. (2026). Graph-Based Integrated Gradients for Explaining Graph Neural Networks. In Lecture Notes in Computer Science (Vol. 16370 LNAI, pp. 150-162). Springer Nature Singapore. DOI |
| 2026 | Simpson, L., Millar, K., Cheng, A., Lim, C. C., & Chew, H. G. (2026). Probabilistic Lipschitzness and the Stable Rank for Measuring XAI Model Robustness. In Lecture Notes in Computer Science (Vol. 16370 LNAI, pp. 137-149). Springer Nature Singapore. DOI |
| 2025 | Costanza, E., & Simpson, L. (2025). Riemannian Integrated Gradients: A Geometric View of Explainable AI. In F. Nielsen, & F. Barbaresco (Eds.), Geometric Science of Information 7th International Conference, GSI 2025, Saint-Malo, France, October 29–31, 2025, Proceedings, Part I. Springer Nature. |
| Year | Citation |
|---|---|
| 2024 | Simpson, L., Costanza, F., Millar, K., Cheng, A., Lim, C. C., & Chew, H. G. (2024). Algebraic Adversarial Attacks on Integrated Gradients. In Proceedings - International Conference on Machine Learning and Cybernetics (pp. 26-31). Hybrid, Miyazaki: IEEE. DOI Scopus1 |
| 2024 | Simpson, L., Costanza, F., Millar, K., Cheng, A., Lim, C. C., & Chew, H. G. (2024). Tangentially Aligned Integrated Gradients for User-Friendly Explanations. In CEUR Workshop Proceedings Vol. 3910 (pp. 1-12). Dublin, Ireland: CEUR-WS. Scopus1 |
| 2023 | Simpson, L., Millar, K., Cheng, A., Chew, H. G., & Lim, C. C. (2023). A Testbed for Automating and Analysing Mobile Devices and Their Applications. In Proceedings - International Conference on Machine Learning and Cybernetics (pp. 201-208). Online: IEEE. DOI Scopus1 |
| 2022 | Millar, K., Simpson, L., Cheng, A., Chew, H. G., & Lim, C. (2022). Detecting Botnet Victims Through Graph-Based Machine Learning. In 2021 International Conference on Machine Learning and Cybernetics (ICMLC) Vol. 2021-December (pp. 6 pages). online: IEEE. DOI Scopus3 |
| Year | Citation |
|---|---|
| 2025 | Simpson, L., Lawrie, T., Muller, Q., & Adesso, G. (2025). Towards Analogue Wave Computing via Quantum Graph Theory. |
| Year | Citation |
|---|---|
| 2025 | Simpson, L., Costanza, F., Millar, K., Cheng, A., Lim, C. -C., & Chew, H. G. (2025). Algebraic Adversarial Attacks on Explainability Models. |
ANA Partnership Grant Scheme: Physics-Informed Neural Networks for Quantum Graph-Based Medical Imaging Devices
- Autonomous Systems: Marker, Tutor, and Demonstrator
- Control: Marker
- Financial Modelling: Tools and Techniques: Marker and Tutor
- Maths 1A: Marker
- Maths 1B: Marker
- Vector Calculus and Electromagnetics: Marker
- Mathematics for Data Science: Marker
- Artificial Intelligence: Tutor
- Algorithm and Data Structure Analysis: Tutor
- Differential Equations for Engineers: Marker
- Introduction to Financial Mathematics: Marker
- Applications of Quantitative Methods in Finance: Marker
| Date | Role | Research Topic | Location | Program | Supervision Type | Student Load | Student Name |
|---|---|---|---|---|---|---|---|
| 2023 - 2024 | Principal Supervisor | Explainable AI for Graph-based Device Characterisation | University of Adelaide | Summer Vacation Research Project | Other | Full Time | Gerald Freislich |