18277227. MODEL GENERATION DEVICE, SORTING DEVICE, DATA GENERATION DEVICE, MODEL GENERATION METHOD, AND NON-TRANSITORY COMPUTER STORAGE MEDIA simplified abstract (OMRON Corporation)
MODEL GENERATION DEVICE, SORTING DEVICE, DATA GENERATION DEVICE, MODEL GENERATION METHOD, AND NON-TRANSITORY COMPUTER STORAGE MEDIA
Organization Name
Inventor(s)
Tadashi Hyuga of Kyoto-shi, KYOTO (JP)
Mei Tanaka of Kyoto-shi, KYOTO (JP)
MODEL GENERATION DEVICE, SORTING DEVICE, DATA GENERATION DEVICE, MODEL GENERATION METHOD, AND NON-TRANSITORY COMPUTER STORAGE MEDIA - A simplified explanation of the abstract
This abstract first appeared for US patent application 18277227 titled 'MODEL GENERATION DEVICE, SORTING DEVICE, DATA GENERATION DEVICE, MODEL GENERATION METHOD, AND NON-TRANSITORY COMPUTER STORAGE MEDIA
Simplified Explanation: The patent application describes a data generation device that uses a trained encoder to acquire sample points in a feature space and derive a linear sum, then uses a trained decoder to generate new training samples based on the derived linear sum.
- Key Features and Innovation:
- Uses a trained encoder to acquire sample points in a feature space.
- Derives a linear sum based on the acquired sample points.
- Uses a trained decoder to generate new training samples based on the derived linear sum.
Potential Applications: The technology could be applied in various fields such as image processing, data compression, and pattern recognition.
Problems Solved: The technology addresses the need for efficient data generation and sample creation in machine learning and data analysis tasks.
Benefits:
- Enables the creation of new training samples based on existing data.
- Improves the efficiency of data generation processes.
- Enhances the performance of machine learning models.
Commercial Applications: Potential commercial applications include data augmentation tools for machine learning models, image generation software, and data compression algorithms for efficient storage.
Prior Art: Readers can explore prior art related to data generation devices, encoder-decoder models in machine learning, and feature space manipulation techniques.
Frequently Updated Research: Stay updated on advancements in encoder-decoder models, data generation techniques, and applications of feature space manipulation in machine learning.
Questions about Data Generation Devices: 1. What are the key components of a data generation device? 2. How does the trained encoder-decoder model improve data generation processes?
Original Abstract Submitted
A data generation device according to the above-described aspect of the present invention: uses a trained encoder to acquire, in a feature space, two or more sample points corresponding to two or more training samples from among a plurality of training samples, and to derive the linear sum at which the total distance becomes the maximum, said distance being calculated from respective sample points that have been acquired in accordance with a prescribed index; and uses a trained decoder to generate, as a new training sample, a decoding sample corresponding to a feature amount of the derived linear sum.
