Kabushiki kaisha toshiba (20240311632). INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND COMPUTER PROGRAM PRODUCT simplified abstract
Contents
- 1 INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND COMPUTER PROGRAM PRODUCT
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND COMPUTER PROGRAM PRODUCT - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Key Features and Innovation
- 1.6 Potential Applications
- 1.7 Problems Solved
- 1.8 Benefits
- 1.9 Commercial Applications
- 1.10 Questions about the Technology
- 1.11 Original Abstract Submitted
INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND COMPUTER PROGRAM PRODUCT
Organization Name
Inventor(s)
Takeichiro Nishikawa of Yokohama (JP)
INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND COMPUTER PROGRAM PRODUCT - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240311632 titled 'INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND COMPUTER PROGRAM PRODUCT
Simplified Explanation
An information processing device is designed to learn a machine learning model by setting an error function based on weights and features of elements, and then using this function to analyze and output physical quantities of the target.
- The device sets an error function based on weights and features of elements.
- The error function is used during the learning process of a machine learning model.
- The model is learned using the error function to analyze and output physical quantities of the target.
Key Features and Innovation
- Setting an error function based on weights and features of elements.
- Using the error function during the learning process of a machine learning model.
- Analyzing and outputting physical quantities of the target using the learned model.
Potential Applications
This technology can be applied in various fields such as data analysis, pattern recognition, and predictive modeling.
Problems Solved
This technology addresses the need for efficient machine learning models that can accurately analyze and output physical quantities of a target.
Benefits
- Improved accuracy in analyzing and outputting physical quantities.
- Enhanced efficiency in machine learning model learning process.
Commercial Applications
Potential commercial applications include data analytics software, predictive modeling tools, and pattern recognition systems.
Questions about the Technology
How does this technology improve machine learning processes?
This technology improves machine learning processes by setting an error function based on weights and features of elements, leading to more accurate analysis and output of physical quantities.
What are the potential applications of this technology beyond data analysis?
The potential applications of this technology extend to fields such as pattern recognition, predictive modeling, and other areas that require accurate analysis and output of physical quantities.
Original Abstract Submitted
according to an embodiment, an information processing device includes one or more hardware processors configured to: set an error function including one or more terms based on a plurality of weights according to features of a plurality of elements, the error function being a function used during learning of a machine learning model into which positions of a plurality of atoms included in an analysis target, and information indicating which of the plurality of elements the plurality of atoms are, are input, and that outputs a physical quantity of the analysis target; and learn the machine learning model using the error function.