18069719. FEATURE MAP DECOMPOSITION AND OPERATOR DECOMPOSITION IN MACHINE LEARNING OPERATIONS simplified abstract (QUALCOMM Incorporated)
Contents
FEATURE MAP DECOMPOSITION AND OPERATOR DECOMPOSITION IN MACHINE LEARNING OPERATIONS
Organization Name
Inventor(s)
Yeonseok Kim of Bucheon-si (KR)
Kyu Woong Hwang of Daejeon (KR)
FEATURE MAP DECOMPOSITION AND OPERATOR DECOMPOSITION IN MACHINE LEARNING OPERATIONS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18069719 titled 'FEATURE MAP DECOMPOSITION AND OPERATOR DECOMPOSITION IN MACHINE LEARNING OPERATIONS
The present disclosure involves techniques for processing streaming data using machine learning models.
- Generating feature maps for sets of streaming data using a machine learning model
- Combining results of operations on each item in the streaming data into feature maps
- Generating a result based on a combination of the feature maps
Potential Applications: This technology can be applied in real-time data analysis, anomaly detection, and predictive maintenance systems.
Problems Solved: This technology addresses the challenges of processing large volumes of streaming data efficiently and accurately.
Benefits: The technology enables faster and more accurate analysis of streaming data, leading to improved decision-making and operational efficiency.
Commercial Applications: This technology can be used in industries such as finance, healthcare, and manufacturing for real-time data analysis and predictive modeling.
Questions about the technology: 1. How does this technology improve the processing of streaming data compared to traditional methods? 2. What are the key features of the machine learning model used in this technology?
Original Abstract Submitted
Certain aspects of the present disclosure provide techniques for processing streaming data using machine learning models. An example method generally includes generating a first feature map for a first set of streaming data using a machine learning model. To generate the first feature map, results of one or more operations performed on each respective item in the first set of streaming data are combined into the first feature map, and the results of the one or more operations performed for each respective item in the first set of streaming data are combined into the first feature map. A second feature map is generated for a second set of streaming data using the machine learning model. A result of processing the total set of data through the machine learning model is generated based at least on a combination of the first feature map and the second feature map.