Deep Quantum Graph Dreaming: Deciphering Neural Network Insights into Quantum Experiments
Authors:
Preprint
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 (XAI) 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 40 references indexed in Scilit:
- Very-large-scale integrated quantum graph photonicsNature Photonics, 2023
- Multiphoton non-local quantum interference controlled by an undetected photonNature Communications, 2023
- On scientific understanding with artificial intelligenceNature Reviews Physics, 2022
- The potential and global outlook of integrated photonics for quantum technologiesNature Reviews Physics, 2021
- Computer-inspired quantum experimentsNature Reviews Physics, 2020
- Machine learning the thermodynamic arrow of timeNature Physics, 2020
- Progress on Integrated Quantum Photonic Sources with SiliconAdvanced Quantum Technologies, 2019
- A hybrid machine learning algorithm for designing quantum experimentsQuantum Machine Intelligence, 2019
- Learning hard quantum distributions with variational autoencodersnpj Quantum Information, 2018
- Bell’s Theorem, Quantum Theory and Conceptions of the Universe1989