18669790. MACHINE LEARNING DEVICE, MACHINE LEARNING METHOD, AND NON-TRANSITORY COMPUTER-READABLE MEDIUM HAVING MACHINE LEARNING PROGRAM simplified abstract (JVCKENWOOD Corporation)
MACHINE LEARNING DEVICE, MACHINE LEARNING METHOD, AND NON-TRANSITORY COMPUTER-READABLE MEDIUM HAVING MACHINE LEARNING PROGRAM
Organization Name
Inventor(s)
Shingo Kida of Yokohama-shi (JP)
MACHINE LEARNING DEVICE, MACHINE LEARNING METHOD, AND NON-TRANSITORY COMPUTER-READABLE MEDIUM HAVING MACHINE LEARNING PROGRAM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18669790 titled 'MACHINE LEARNING DEVICE, MACHINE LEARNING METHOD, AND NON-TRANSITORY COMPUTER-READABLE MEDIUM HAVING MACHINE LEARNING PROGRAM
The abstract describes a patent application for a system that includes a feature extraction unit, a semantic prediction unit, a mapping unit, and an optimization unit. The feature extraction unit extracts a feature vector from input data, the semantic prediction unit generates a semantic vector from the feature vector, the mapping unit generates a semantic vector from the feature vector, and the optimization unit optimizes parameters of the mapping unit using the semantic vector generated by the semantic prediction unit.
- Feature extraction unit extracts a feature vector from input data
- Semantic prediction unit generates a semantic vector from the feature vector
- Mapping unit generates a semantic vector from the feature vector
- Optimization unit optimizes parameters of the mapping unit using the semantic vector
- Minimizes distance between the semantic vector generated by the mapping unit and the correct answer semantic vector
Potential Applications: - Image recognition systems - Natural language processing applications - Autonomous vehicles - Medical diagnosis systems - Fraud detection algorithms
Problems Solved: - Enhances accuracy of semantic predictions - Improves efficiency of feature extraction - Enables better classification of input data - Facilitates meta-learning processes - Enhances performance of machine learning models
Benefits: - Increased accuracy in data classification - Improved efficiency in feature extraction - Enhanced performance of machine learning models - Facilitates meta-learning processes - Enables better prediction of semantic information
Commercial Applications: Title: "Enhanced Semantic Prediction System for Improved Data Classification" This technology can be used in various industries such as healthcare, finance, e-commerce, and security for improving data classification accuracy, enhancing predictive analytics, and optimizing machine learning models.
Questions about the technology: 1. How does the optimization unit improve the performance of the mapping unit? 2. What are the potential drawbacks of using this system in real-world applications?
Original Abstract Submitted
A feature extraction unit extracts a feature vector from input data. A semantic prediction unit is a module has been trained in advance in a meta-learning process and that generates a semantic vector from the feature vector of the input data. A mapping unit is a module that has learned a base class and that generates a semantic vector from the feature vector of the input data. An optimization unit optimizes parameters of the mapping unit using the semantic vector generated by the semantic prediction unit as a correct answer semantic vector such that a distance between the semantic vector generated by the mapping unit and the correct answer semantic vector is minimized when semantic information is not added to input data of a novel class at the time of learning the novel class.
