自动网络结构 通过知识蒸发现基于物理的神经网络
Ziti Liu1,2, Yang Liu2, Xunshi Yan3
1School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China.
Nature communications
|October 30, 2025
概括
本研究引入了一种用于部分微分方程 (PDEs) 的神经网络中发现结构的新方法. 该方法通过将物理定律自动嵌入到网络架构中来提高准确性和效率.
科学领域:
- 计算物理学的计算物理.
- 机器学习用于科学建模.
背景情况:
- 部分微分方程 (PDEs) 对于建模物理现象至关重要.
- 当前的物理信息神经网络 (PINNs) 由于依赖外部损失函数,难以自动发现和嵌入物理结构.
研究的目的:
- 为PDEs开发一种自动发现和嵌入物理一致结构在神经网络中的方法.
- 为科学应用提高神经网络模型的准确性,效率和适应性.
主要方法:
- 基于物理的蒸来解物理和参数规范化.
- 使用教师和学生网络进行分阶段优化.
- 聚类和参数重建用于结构提取.
主要成果:
- 成功地从PDEs中提取了相关的物理结构.
- 与传统方法相比,证明了提高准确性和培训效率.
- 在不同物理问题中展示了增强的结构适应性和可转移性.
结论:
- 提出的方法为PDEs的结构化神经网络的高效建模和自动发现提供了一个新的视角.
- 这种方法有助于创建更易于解释和更强大的基于物理的机器学习模型.
相关概念视频
01:01Neuroplasticity
1.6K
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
1.6K
01:25Neural Circuits
2.6K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
2.6K