.png){kind=icon}
返回
Learning Interacting Theories from Data
.png){kind=icon}
OA
AI
DOI：10.1103/PhysRevX.13.041033.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
One challenge of physics is to explain how collective properties arise from microscopic interactions. Indeed, interactions form the building blocks of almost all physical theories and are described by polynomial terms in the action. The traditional approach is to derive these terms from elementary processes and then use the resulting model to make predictions for the entire system. But what if the underlying processes are unknown? Can we reverse the approach and learn the microscopic action by observing the entire system? We use invertible neural networks to first learn the observed data distribution. By the choice of a suitable nonlinearity for the neuronal activation function, we are then able to compute the action from the weights of the trained model; a diagrammatic language expresses the change of the action from layer to layer. This process uncovers how the network hierarchically constructs interactions via nonlinear transformations of pairwise relations. We test this approach on simulated datasets of interacting theories and on an established image dataset (MNIST). The network consistently reproduces a broad class of unimodal distributions; outside this class, it finds effective theories that approximate the data statistics up to the third cumulant. We explicitly show how network depth and data quantity jointly improve the agreement between the learned and the true model. This work shows how to leverage the power of machine learning to transparently extract microscopic models from data.
Keyword:
Complex Systems
Interdisciplinary Physics
Statistical Physics
期刊
IF:
15.7
论文数:
2.7K
被引数:
3.4W
机构
引用论文
The Late Paleozoic continental margin tectonic evolution at the eastern margin of the Jiamusi Block
PREAI
分享收藏‘Invisible actors’—How poor methodology reporting compromises mouse models of oncology: A cross-sectional survey.png)
PLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏Separability and geometry of object manifolds in deep neural networksNATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏
查看更多内容