Deep quantum graph dreaming: deciphering neural network insights into quantum experiments
Open Access
- 15 February 2024
- journal article
- research article
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 5 (1) , 015029
Abstract
Despite their promise to facilitate new scientific discoveries, the opaqueness of neural networks presents a challenge in interpreting the logic behind their findings. Here, we use a eXplainable-AI technique called inception or deep dreaming, which has been invented in machine learning for computer vision. We use this technique to explore what neural networks learn about quantum optics experiments. Our story begins by training deep neural networks on the properties of quantum systems. Once trained, we ‘invert’ the neural network—effectively asking how it imagines a quantum system with a specific property, and how it would continuously modify the quantum system to change a property. We find that the network can shift the initial distribution of properties of the quantum system, and we can conceptualize the learned strategies of the neural network. Interestingly, we find that, in the first layers, the neural network identifies simple properties, while in the deeper ones, it can identify complex quantum structures and even quantum entanglement. This is in reminiscence of long-understood properties known in computer vision, which we now identify in a complex natural science task. Our approach could be useful in a more interpretable way to develop new advanced AI-based scientific discovery techniques in quantum physics.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- A hybrid machine learning algorithm for designing quantum experimentsQuantum Machine Intelligence, 2019
- Quantum experiments and graphs II: Quantum interference, computation, and state generationProceedings of the National Academy of Sciences, 2019
- Machine learning method for state preparation and gate synthesis on photonic quantum computersQuantum Science and Technology, 2019
- Learning hard quantum distributions with variational autoencodersnpj Quantum Information, 2018
- Quantum Experiments and Graphs: Multiparty States as Coherent Superpositions of Perfect MatchingsPhysical Review Letters, 2017
- Machine learning of explicit order parameters: From the Ising model to SU(2) lattice gauge theoryPhysical Review B, 2017
- Probing many-body localization with neural networksPhysical Review B, 2017
- Entanglement by Path IdentityPhysical Review Letters, 2017
- Automated Search for new Quantum ExperimentsPhysical Review Letters, 2016
- Bell’s theorem with and without inequalities for the three-qubit Greenberger-Horne-Zeilinger andWstatesPhysical Review A, 2002