International business machines corporation (20240135241). INTELLIGENT DEVICE DATA FILTER FOR MACHINE LEARNING simplified abstract

INTELLIGENT DEVICE DATA FILTER FOR MACHINE LEARNING

Organization Name

international business machines corporation

Inventor(s)

Janice Yang of Cambridge MA (US)

Kate Hogan of St. Louis MO (US)

Arnav Aggarwal of Los Altos CA (US)

Ethan Weaver of Morgantown WV (US)

John S. Werner of Fishkill NY (US)

INTELLIGENT DEVICE DATA FILTER FOR MACHINE LEARNING - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240135241 titled 'INTELLIGENT DEVICE DATA FILTER FOR MACHINE LEARNING

Simplified Explanation

The patent application describes a method where a processor at an edge device running a local instance of a machine learning model receives a set of inference data, determines the probability for each datapoint to be sent back to the cloud environment for retraining the model, and sends back only the datapoints that meet a certain threshold.

• The processor receives inference data at an edge device running a local instance of a machine learning model.
• The machine learning model was trained in a cloud environment and then deployed to the edge device.
• The processor runs the datapoints through filters to determine the probability of sending each datapoint back to the cloud for retraining.
• For each datapoint, the processor checks if the probability meets a threshold required for sending it back to the cloud.

Potential Applications

This technology could be applied in various industries such as healthcare, finance, and manufacturing for real-time model optimization and continuous learning.

Problems Solved

1. Efficient model retraining: The method allows for selective sending of datapoints for retraining, saving computational resources. 2. Real-time model improvement: By sending only relevant datapoints back to the cloud, the model can be continuously improved based on new data.

Benefits

1. Cost-effective: Reduces the need to send all data back to the cloud for retraining, saving on bandwidth and processing costs. 2. Improved model accuracy: By selectively sending back datapoints, the model can be updated with more relevant and recent data, leading to better performance.

Potential Commercial Applications

Optimizing machine learning models in edge devices for industries such as predictive maintenance, anomaly detection, and personalized recommendations.

Possible Prior Art

One possible prior art could be a similar method used in distributed computing systems where data is selectively sent back to a central server for processing based on certain criteria.

Unanswered Questions

How does the method handle data privacy and security concerns when sending data back to the cloud for retraining?

The patent application does not provide details on how data privacy and security are maintained during the process of sending datapoints back to the cloud for retraining.

What are the specific filters used by the processor to determine the probability of sending each datapoint back to the cloud?

The patent application does not specify the exact filters or criteria used by the processor to calculate the probability for each datapoint.

Original Abstract Submitted

in an approach, a processor receives, at an edge device running a local instance of a machine learning (ml) model, a set of inference data comprising a plurality of datapoints, wherein the local instance of the ml model is a deployed version of the ml model running in a cloud environment, and wherein the ml model was trained in the cloud environment and then deployed to the edge device. a processor runs the plurality of datapoints through one or more filters to determine a probability for each datapoint of whether a respective datapoint should be sent back to the cloud environment and used for retraining the ml model. a processor determines, for each datapoint, whether the probability for the respective datapoint meets a send back threshold that is required to be met before the respective datapoint is sent back to the cloud environment.