Micron technology, inc. (20240220860). MACHINE LEARNING MODEL AGGREGATION simplified abstract
Contents
MACHINE LEARNING MODEL AGGREGATION
Organization Name
Inventor(s)
Pavana Prakash of Houston TX (US)
Shashank Bangalore Lakshman of Folsom CA (US)
Saideep Tiku of Fort Collins CO (US)
MACHINE LEARNING MODEL AGGREGATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240220860 titled 'MACHINE LEARNING MODEL AGGREGATION
The patent application describes methods and systems for aggregating machine learning models to predict the aging of memory devices.
- The system includes a first computing device, a second computing device, a local federated server, and a global federated server.
- The first and second computing devices train machine learning models based on memory usage data and device characteristic data from memory devices.
- The local federated server aggregates the first and second machine learning models into a third model.
- The global federated server aggregates the third model with other models to predict the aging of memory devices.
Potential Applications: - Predictive maintenance for memory devices - Optimization of memory device performance - Data center management for memory devices
Problems Solved: - Predicting memory device aging accurately - Efficiently aggregating machine learning models - Improving memory device lifespan
Benefits: - Enhanced memory device reliability - Cost savings through predictive maintenance - Optimized performance of memory devices
Commercial Applications: Title: Predictive Memory Device Maintenance System This technology can be used in data centers, IoT devices, and other systems relying on memory devices. It can help companies save costs by predicting memory device failures before they occur.
Questions about Machine Learning Model Aggregation: 1. How does the system ensure the accuracy of predicting memory device aging? The system uses aggregated machine learning models to improve prediction accuracy by considering various factors affecting memory device lifespan.
2. What are the potential challenges in implementing this technology in real-world applications? Implementing this technology may require significant computational resources and data processing capabilities to handle large amounts of memory usage data effectively.
Original Abstract Submitted
methods and systems associated with a machine learning model aggregation are described. a system can include a first computing device, a second computing device, a local federated server, and a global federated server. the first computing device and the second computing device can train respective first and second machine learning models based on gathered memory usage data and device characteristic data associated with a respective first plurality of memory devices and second plurality of memory devices. the local federated server can aggregate the first machine learning model and the second machine learning model into a third machine learning model. the global federated server can aggregate the third machine learning model with a fourth machine learning model comprising a plurality of aggregated machine learning models into a fifth machine learning model and predict aging of the first plurality of memory devices and the second plurality of memory devices.
