.png){kind=icon}
返回
Deep quantum graph dreaming: deciphering neural network insights into quantum experiments
.png){kind=icon}
OA
AI
DOI：10.1088/2632-2153/ad2628.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
neural network interpretability
deep dreaming
quantum physics
期刊
M
IF:
4.6
论文数:
1.1K
被引数:
3.4K
机构
引用论文
.png){kind=icon}
Machine learning method for state preparation and gate synthesis on photonic quantum computers用于光子量子计算机的状态准备和门合成的机器学习方法
OAAI
OAAI分享收藏A Coupled Resonator Decoupling Network for Two-Element Compact Antenna Arrays in Mobile Terminals
PREAI
分享收藏
查看更多内容