通过学习神经网络潜力的多体函数的相关性,探黑子的内部
Klara Bonneau1, Jonas Lederer2,3, Clark Templeton4
1Department of Physics, Freie Universität Berlin, Berlin, Germany.
Nature communications
|November 10, 2025
概括
可解释的人工智能 (XAI) 工具现在用于解释基于图形神经网络的机器学习潜力 (MLP). 这种方法将复杂的能量模型分解为可理解的n-body相互作用,而不会失去准确性.
科学领域:
- 计算化学计算化学
- 材料科学 材料科学 材料科学
- 人工智能的人工智能
背景情况:
- 使用人工神经网络 (ANN) 的机器学习潜力 (MLP) 越来越多地用于以原子或粗粒度分辨率建模复杂系统.
- 在MLP中ANN的一个主要局限性是与传统的,更简单的功能形式相比,它们缺乏可解释性.
- 这种不透明性阻碍了理解他们预测的物理基础.
研究的目的:
- 提高基于图形神经网络 (GNN) 的粗粒度MLP的解释性.
- 适应可解释的人工智能 (XAI) 技术来分析基于GNN的MLP.
- 为了证明可解释的MLP保留了预测准确性.
主要方法:
- 应用 XAI 工具对基于 GNN 的粗粒度潜力.
- 将MLP分解为n体相互作用.
- 对粗粒度系统的验证:甲流体,水流体和NTL9蛋白.
主要成果:
- 该XAI方法成功地将基于GNN的MLPs分解成可解释的n-body术语.
- 解释提供了人类对学习的能量模型的可理解的见解.
- 分解并没有影响MLP的预测能力.
结论:
- XAI工具可以使基于GNN的MLP更易于解释,解决一个主要的批评.
- 开发的方法允许将复杂的潜能分解为可理解的物理相互作用.
- 训练有素的MLP学习与基本原则相一致的有意义的物理交互.
相关概念视频
Propagation of Action Potentials
8.8K
The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
8.8K
Postsynaptic Potential (PSP)
4.8K
Postsynaptic potential (PSP) refers to a change in the electrical potential of a neuron when neurotransmitters released by presynaptic neurons bind to postsynaptic receptors. This potential can either be excitatory, leading to depolarization and ultimately action potential generation, or inhibitory, leading to hyperpolarization and suppression of the postsynaptic neuron.
There are two types of receptors: ionotropic and metabotropic.
The ionotropic receptor is the membrane protein that has an...
There are two types of receptors: ionotropic and metabotropic.
The ionotropic receptor is the membrane protein that has an...
4.8K
Neural 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
Graded Potential
6.8K
Graded potentials are localized fluctuations in the cell membrane's electrical charge, commonly found in the dendrites of neurons. The magnitude of these potential changes depends on the strength of the initiating stimulus. In a membrane at its resting potential, a graded potential signifies a voltage shift either above -70 mV or below -70 mV.
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...
6.8K
Neural Regulation
43.1K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
43.1K
Integration of Synaptic Events
3.4K
Synaptic integration mainly includes the summation of graded potentials. Graded potentials, regardless of their type, cause subtle alterations in membrane voltage, resulting in either depolarization or hyperpolarization. These incremental changes, when combined or summed, can propel the neuron toward its threshold. Consider, for example, a membrane experiencing a +15 mV shift, causing it to depolarize from -70 mV to -55 mV. In this scenario, graded potentials govern the membrane's ability to...
3.4K


