Video Experimental Relacionado
Updated: Jan 28, 2026
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.9K
ZORANet: Redes neuronales fermiónicas relativistas basadas en la aproximación regular de orden cero
Mengsa Wang1,2, Yuzhi Zhou2,3, Han Wang4,5
1Graduate School of China Academy of Engineering Physics, Beijing 100088, China.
Journal of chemical theory and computation
|January 26, 2026
Resumen
ZORANet, una nueva red neuronal fermiónica, permite cálculos precisos de química cuántica relativista. Mejora los métodos existentes para la estructura electrónica, tratando la correlación electrónica y los efectos relativistas de manera eficiente.
Área de la Ciencia:
- Química computacional
- Mecánica cuántica
- Inteligencia artificial en la ciencia
Sus antecedentes:
- Los efectos relativistas son cruciales para cálculos precisos de estructura electrónica, especialmente para elementos pesados.
- Los métodos existentes de redes neuronales profundas enfrentan desafíos en el manejo de problemas de química cuántica relativista.
- La aproximación regular de orden cero (ZORA) escalar es una aproximación relativista común, pero sufre de errores dependientes de la galga.
Objetivo del estudio:
- Introducir ZORANet, un novedoso marco de red neuronal fermiónica para cálculos de estructura electrónica relativista utilizando ZORA escalar.
- Abordar los desafíos numéricos en los cálculos relativistas, incluida la corrección de la cuspide electrón-núcleo y el muestreo por importancia.
- Desarrollar variantes (ZORANet escalado, ZORANet atómico) para mitigar los errores dependientes de la galga de ZORA.
Principales métodos:
- Se desarrolló ZORANet, un marco de red neuronal fermiónica basado en ZORA escalar.
- Se implementó la corrección de la cuspide electrón-núcleo y el muestreo por importancia para la estabilidad del entrenamiento y la reducción de errores.
- Se crearon variantes escaladas de ZORANet y atómicas de ZORANet para abordar la dependencia de la galga.
Principales resultados:
- Las energías de ZORANet y ZORANet escalado muestran un excelente acuerdo con los resultados exactos de ZORA y Dirac para sistemas similares al hidrógeno.
- ZORANet logra la precisión química para potenciales de ionización y afinidades electrónicas de elementos de primera y segunda fila, superando a FermiNet.
- Atomic ZORANet iguala la precisión de vanguardia para las energías de disociación de hidruros, superando a FermiNet.
Conclusiones:
- ZORANet es un método de todos los electrones de alta precisión para química cuántica relativista.
- Trata eficazmente la correlación electrónica y los efectos relativistas con un costo computacional comparable al de FermiNet.
- ZORANet muestra una gran promesa para el desarrollo de métodos integrales de química cuántica relativista ab initio.
Videos de Conceptos Relacionados
01:14Zeroth Law of Thermodynamics
7.0K
Experimentally, if object A is in equilibrium with object B, and object B is in equilibrium with object C, then object A is in equilibrium with object C. That statement of transitivity is called the "zeroth law of thermodynamics." For example, a cold metal block and a hot metal block are both placed on a metal plate at room temperature. Eventually, the cold block and the plate will be in thermal equilibrium. In addition, the hot block and the plate will be in thermal equilibrium.
7.0K
01:26Linearization and Approximation
53
Linearization is a mathematical technique used to approximate complex, nonlinear functions with simpler linear models in the vicinity of a chosen reference point. The method is based on the idea that, although a function may be difficult to evaluate exactly, its behavior near a specific input value can often be closely approximated by the tangent line at that point. This approach is particularly useful when small deviations from a known value are involved.Consider the square root function, for...
53
01:29Application of Linearization and Approximation
87
A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...
87
01:28Accuracy, limits, and approximation
1.3K
Accuracy, limits, and approximations are common in many fields, especially in engineering calculations. These concepts are imperative for ensuring that a given value is as close as possible to its true value.
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
1.3K
01:26Linear Approximation in Frequency Domain
367
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
367
01:21Linear Approximation in Time Domain
366
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
366