Skip to main content

AI meets Quantum: Quantum algorithms for knowledge representation and learning - Student: Guangxi Li

Project Member(s): Feng, Y., Li, S.

Funding or Partner Organisation: Sydney Quantum Academy
Sydney Quantum Academy

Start year: 2020

Summary: Quantum machine learning is an emerging research direction which aims to improve classical machine learning algorithms using the quantum information processing. Wherein the most important direction ought to be quantum neural network thanks to the huge success of neural networks. However, this, currently, is only an ideal proposal because of i) the characteristics of a black box in neural networks and ii) the lack of universal quantum computers. Therefore, several works are taking a step back to concentrate on the relationships between neural networks and quantum states. Fortunately, such relationships, for example equivalence or conversion relations, can be built easily through tensor networks. We will, along this direction, continuously do our best to reveal more information about neural networks and quantum states via tensor networks. If possible, we will propose some quantum neural network algorithm, such as quantum capsule networks or other quantum shallow networks, based on the existing or newly proposed information. This research will help us understand neural networks better and developing quantum neural networks efficiently.

FOR Codes: Expanding Knowledge in the Information and Computing Sciences, Artificial Intelligence and Image Processing not elsewhere classified, Quantum Information, Computation and Communication, Graphics, augmented reality and games not elsewhere classified, Quantum information, computation and communication