18393357. MACHINE LEARNING MODEL AGGREGATION simplified abstract (MICRON TECHNOLOGY, INC.)
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 18393357 titled 'MACHINE LEARNING MODEL AGGREGATION
Simplified Explanation: The patent application describes methods and systems for aggregating machine learning models to predict aging of memory devices.
- Memory usage data and device characteristic data are gathered from multiple memory devices.
- First and second computing devices train machine learning models based on this data.
- A local federated server aggregates these models into a third machine learning model.
- A global federated server further aggregates this model with others to predict aging of memory devices.
Key Features and Innovation:
- Aggregation of machine learning models to predict aging of memory devices.
- Use of memory usage data and device characteristic data for training models.
- Local and global federated servers for model aggregation.
Potential Applications: This technology can be applied in various industries such as:
- Predictive maintenance in manufacturing.
- Health monitoring in IoT devices.
- Performance optimization in data centers.
Problems Solved:
- Efficient prediction of memory device aging.
- Utilization of aggregated machine learning models.
- Improved maintenance scheduling based on predictive analytics.
Benefits:
- Enhanced reliability of memory devices.
- Cost savings through proactive maintenance.
- Optimized performance of memory systems.
Commercial Applications: Title: Predictive Memory Device Aging Analysis Technology This technology can be utilized in:
- Semiconductor manufacturing for quality control.
- IoT device management for predictive maintenance services.
- Cloud computing for optimizing memory usage.
Prior Art: Prior research may include studies on federated learning and predictive maintenance in the semiconductor industry.
Frequently Updated Research: Stay updated on advancements in federated learning techniques and predictive maintenance algorithms for memory devices.
Questions about Predictive Memory Device Aging Analysis Technology: 1. How does this technology improve memory device maintenance processes? 2. What are the potential cost savings for companies implementing this predictive analysis technology?
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.
