Deep Quantum Graph Dreaming: Deciphering Neural Network Insights into Quantum Experiments
Tareq Jaouni, S\"oren Arlt, Carlos Ruiz-Gonzalez, Ebrahim Karimi,, Xuemei Gu, Mario Krenn

TL;DR
This paper applies an explainable AI technique called deep dreaming to neural networks trained on quantum optics data, revealing how the networks understand simple and complex quantum properties, including entanglement.
Contribution
It introduces the use of deep dreaming for interpreting neural networks in quantum physics, uncovering how they learn and represent quantum properties and structures.
Findings
Neural networks can shift quantum property distributions.
Deeper layers identify complex quantum structures and entanglement.
The approach enhances interpretability of AI in quantum science.
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 or , 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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsExplainable Artificial Intelligence (XAI) · Computational Physics and Python Applications · Data Visualization and Analytics
