17987530. REPRESENTING ATOMIC STRUCTURES AS A GAUSSIAN PROCESS simplified abstract (Toyota Jidosha Kabushiki Kaisha)
Contents
- 1 REPRESENTING ATOMIC STRUCTURES AS A GAUSSIAN PROCESS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 REPRESENTING ATOMIC STRUCTURES AS A GAUSSIAN PROCESS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
REPRESENTING ATOMIC STRUCTURES AS A GAUSSIAN PROCESS
Organization Name
Toyota Jidosha Kabushiki Kaisha
Inventor(s)
[[:Category:Jens Strabo Hummelsh�j of Millbrae CA (US)|Jens Strabo Hummelsh�j of Millbrae CA (US)]][[Category:Jens Strabo Hummelsh�j of Millbrae CA (US)]]
Joseph Harold Montoya of Millbrae CA (US)
REPRESENTING ATOMIC STRUCTURES AS A GAUSSIAN PROCESS - A simplified explanation of the abstract
This abstract first appeared for US patent application 17987530 titled 'REPRESENTING ATOMIC STRUCTURES AS A GAUSSIAN PROCESS
Simplified Explanation
The method described in the patent application involves representing atomic structures as Gaussian processes by mapping crystal structures of chemical elements in real space and learning a 3D embedding of each element using a machine learning model. The model is trained based on the representation of atoms in the unit cell of the crystal structure, and can predict material properties at specific points in real space.
- Mapping crystal structures of chemical elements in real space
- Learning 3D embeddings of chemical elements using a machine learning model
- Training the model based on the representation of atoms in the unit cell
- Predicting material properties at specific points in real space
Potential Applications
This technology could be applied in materials science, chemistry, and physics for predicting material properties and understanding atomic structures.
Problems Solved
This method helps in accurately representing atomic structures and predicting material properties, which can aid in the development of new materials with desired characteristics.
Benefits
The benefits of this technology include improved accuracy in representing atomic structures, efficient prediction of material properties, and potential for discovering novel materials.
Potential Commercial Applications
One potential commercial application of this technology could be in the development of advanced materials for various industries, such as electronics, aerospace, and energy.
Possible Prior Art
One possible prior art could be the use of machine learning models for predicting material properties based on atomic structures, but the specific method of representing atomic structures as Gaussian processes may be novel.
=== What are the limitations of this method in predicting material properties accurately? The abstract does not mention any limitations of the method in predicting material properties accurately.
=== How does this method compare to traditional methods of representing atomic structures in terms of computational efficiency? The abstract does not provide information on how this method compares to traditional methods in terms of computational efficiency.
Original Abstract Submitted
A method for representing atomic structures as Gaussian processes is described. The method includes mapping a crystal structure of chemical elements in a real space, in which atoms of the chemical elements are represented in a unit cell. The method also includes learning, by a machine learning model, a 3D embedding of each of the chemical elements in the real space according to the mapping of the crystal structure of the chemical elements. The method further includes training the machine learning model according to a representation of the atoms of the chemical elements in the unit cell based on the mapping of the crystal structure of the chemical elements. The method also includes predicting a material property corresponding to a point within the real space.