18414526. INFORMATION SYSTEM FOR GENERATION OF NEW MOLECULE BY USING GRAPH REPRESENTING MOLECULE simplified abstract (NEC Corporation)
Contents
- 1 INFORMATION SYSTEM FOR GENERATION OF NEW MOLECULE BY USING GRAPH REPRESENTING MOLECULE
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 INFORMATION SYSTEM FOR GENERATION OF NEW MOLECULE BY USING GRAPH REPRESENTING MOLECULE - 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 Prior Art
- 1.11 Frequently Updated Research
- 1.12 Questions about Machine Learning Method for Learning and Applying a Rule Set from Relational Data
- 1.13 Original Abstract Submitted
INFORMATION SYSTEM FOR GENERATION OF NEW MOLECULE BY USING GRAPH REPRESENTING MOLECULE
Organization Name
Inventor(s)
Francesco Alesiani of Heidelberg (DE)
Markus Zopf of Heidelberg (DE)
INFORMATION SYSTEM FOR GENERATION OF NEW MOLECULE BY USING GRAPH REPRESENTING MOLECULE - A simplified explanation of the abstract
This abstract first appeared for US patent application 18414526 titled 'INFORMATION SYSTEM FOR GENERATION OF NEW MOLECULE BY USING GRAPH REPRESENTING MOLECULE
Simplified Explanation
The patent application describes a machine learning method for learning and applying a rule set from relational data, such as medical data, by generating an intermediate representation of the data and learning optimized logical rules based on this representation.
Key Features and Innovation
- Machine learning method for learning and applying rules from relational data.
- Graph representation of relational data with nodes and edges.
- Intermediate vector representation of the graph features.
- Learning optimized logical rules using a MAX-SAT problem and gradient estimation.
- Application of optimized rules to new data for tasks like disease prediction.
Potential Applications
The technology can be used in various machine learning tasks, such as disease prediction using medical data, optimization of machine learning tasks, and supporting decision-making processes.
Problems Solved
- Efficient learning and application of rules from relational data.
- Optimization of machine learning tasks using logical rules.
- Improved decision-making based on learned rules from data.
Benefits
- Enhanced accuracy in disease prediction.
- Streamlined machine learning processes.
- Better support for decision-making based on learned rules.
Commercial Applications
- Healthcare industry for disease prediction.
- Data analysis companies for optimizing machine learning tasks.
- Decision support systems for various industries.
Prior Art
There is ongoing research in the field of machine learning and relational data analysis, but this specific method of learning optimized logical rules from an intermediate representation appears to be novel.
Frequently Updated Research
There may be new developments in machine learning algorithms for relational data analysis that could impact the efficiency and accuracy of rule learning methods.
Questions about Machine Learning Method for Learning and Applying a Rule Set from Relational Data
Question 1
How does this machine learning method differ from traditional rule-based systems?
Traditional rule-based systems rely on manually defined rules, while this method learns optimized logical rules from relational data using a machine learning approach.
Question 2
What are the potential challenges in applying this technology to real-world data sets?
One potential challenge could be the scalability of the method to large and complex relational data sets, as well as the interpretability of the learned rules in practical applications.
Original Abstract Submitted
A machine learning method for learning and applying a rule set from relational data includes receiving a graph representing relational data, wherein nodes represent elements of the graph, and edges represent relationships between nodes, and generating an intermediate representation of the graph by mapping features of the nodes and edges of the graph to an intermediate vector representation. Optimized logical rules that define the nodes and edges of the graph based on the intermediate vector representation are learned by: defining a maximum satisfiability (MAX-SAT) problem for the graph; and estimating a gradient around a solution of the MAX-SAT problem to produce the optimized logical rules, which are applied to a new graph. The data can be medical data and the graph can be used in a machine-learning task, such as using the medical data for disease prediction, for optimization of the machine-learning task and/or to support decision-making.
