Projects
Current Projects
(2025) Physic-informed Quantum Machine Learning
Quantum machine learning (QML) has emerged as a promising approach to tackle complex problems that classical methods struggle to solve efficiently. In this paper, we explore the use of parameterized quantum circuits (PQCs) to learn and approximate solutions to PDEs. Especially ones that related to physics problems.
Outcomes:
- Thanh Nguyen et. al. (2025): "Physic informed Quantum Machine Learning: Solving simple Harmonic Oscillation PDE." In Preparation of Papers for IEEE TRANSACTIONS and JOURNALS (Advanced Draft).
(2023) The Impact of Barren Plateaus Mitigation Strategy on the Quantum Neural Network Capacity to Learn
Thanh Nguyen, Supervised by Prof. Jacob Cybulski (Deakin SIT)
Methodology and Tools used: Quantum Computing, Quantum Machine Learning, IBM Quantum, Python QISKIT, Torch, SkLearn.
Training of quantum neural networks (QNN) is commonly affected by the emergence of barren plateaus (large flat areas in the loss function landscape), which impede the convergence of QNN parameter optimisation. Such training problems are known to be caused by large quantum circuits, poor initialisation of QNN parameters, or the selection of an inferior cost function. Fortunately, there are well established techniques of mitigating the formation of barren plateaus, such as restricting the circuit depth, layerwise development of QNN circuits and a careful planning of the parameter initialisation process. While dealing with barren plateaus, their mitigation strategies are expected to have a positive impact on the QNN training, however, in some cases while training convergence improves the overall QNN performance degrades.
This project thus investigates an impact of barren plateaus mitigation strategy on the QNN capacity to learn, as measured by the network's local effective dimension, which is a dynamic statistical measure of the system's ability to generalise beyond the data used in its training.
Outcomes:
- Nguyen Ngo Cong Thanh and Jacob L. Cybulski (2023): "Investigation of Barren Plateaus in Quantum Neural Network Development." Presented at 10th International Congress on Industrial and Applied Mathematics (ICIAM 2023), Waseda University, Tokyo, Japan, 20-25 Aug, 2023.
- Cybulski, J.L., Nguyen, T. Impact of barren plateaus countermeasures on the quantum neural network capacity to learn. Quantum Inf Process 22, 442 (2023). https://doi.org/10.1007/s11128-023-04187-8 .
- Thanh Nguyen and Jacob L. Cybulski (2023): "Training Variational Quantum Models with Barren Plateaus Mitigation Strategies." In Preparation for journal submission (Advanced Draft).
(2023) Applications of Quantum Algorithms in Finance
Thanh Nguyen and H.L. Thi
The Quantum processors' performance is predicted to surpass the traditional systems during this decade in computational performance and capabilities. This disruptive technology can significantly impact many industrial sectors in the long term. Other than communication and mathematics, we expect the finance sector to be one of the first to receive the prosperity of this new cutting-edge technology.
Outcomes:
-
Cong, T.N.N., Thi, H.L. (2024), "Variational Quantum Algorithms in Finance - A Review." Presented at the 9th International Congress on Information and Communication Technology, London, United Kingdom, 19-22 Feb, 2024.
-
Thi, H.L., Nguyen, T. (2024). Variational Quantum Algorithms in Anomaly Detection, Fraud Indicator Identification, Credit Scoring, and Stock Price Prediction. In: Yang, XS., Sherratt, S., Dey, N., Joshi, A. (eds) Proceedings of Ninth International Congress on Information and Communication Technology. ICICT 2024 2024. Lecture Notes in Networks and Systems, vol 1003. Springer, Singapore. https://doi.org/10.1007/978-981-97-3302-6_39.
-
Cong, T.N.N., Thi, H.L. (2024). Variational Quantum Algorithms in Finance. In: Yang, XS., Sherratt, S., Dey, N., Joshi, A. (eds) Proceedings of Ninth International Congress on Information and Communication Technology. ICICT 2024 2024. Lecture Notes in Networks and Systems, vol 1002. Springer, Singapore. https://doi.org/10.1007/978-981-97-3299-9_2.