Samsung electronics co., ltd. (20240135181). SYSTEMS AND METHODS FOR ON-DEVICE VALIDATION OF A NEURAL NETWORK MODEL simplified abstract

SYSTEMS AND METHODS FOR ON-DEVICE VALIDATION OF A NEURAL NETWORK MODEL

Organization Name

samsung electronics co., ltd.

Inventor(s)

Gokulkrishna M of Bengaluru (IN)

Siva Kailash Sachithanandam of Bengaluru (IN)

Prasanna R of Bengaluru (IN)

Rajath Elias Soans of Bengaluru (IN)

Alladi Ashok Kumar Senapati of Bengaluru (IN)

Praveen Doreswamy Naidu of Bengaluru (IN)

Pradeep Nelahonne Shivamurthappa of Bengaluru (IN)

SYSTEMS AND METHODS FOR ON-DEVICE VALIDATION OF A NEURAL NETWORK MODEL - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240135181 titled 'SYSTEMS AND METHODS FOR ON-DEVICE VALIDATION OF A NEURAL NETWORK MODEL

Simplified Explanation

The abstract describes a method for validating a trained artificial intelligence model on a device by deploying a validation model that incorporates anticipated configurational changes and actual deviations that occurred during training. Input data is provided to both the validation model and the trained AI model to compare their outputs and validate the trained AI model.

• Explanation of the patent/innovation:

 * Deploy a validation model with anticipated configurational changes and actual deviations.
 * Provide input data to both the validation model and the trained AI model.
 * Compare the outputs of both models to validate the trained AI model.

1. 1. 1. Potential Applications:

This technology could be applied in various industries such as healthcare, finance, and manufacturing to ensure the accuracy and reliability of AI models deployed on devices.

1. 1. 1. Problems Solved:

This technology addresses the challenge of validating trained AI models on devices in real-world scenarios where configurational changes and deviations may occur during training.

1. 1. 1. Benefits:

The method provides a systematic approach to validate AI models, improving their performance and reliability in practical applications.

1. 1. 1. Potential Commercial Applications:

Companies developing AI solutions for edge devices could benefit from this technology to ensure the accuracy and robustness of their models in real-world environments.

1. 1. 1. Possible Prior Art:

Prior art may include methods for validating AI models on devices, but the specific approach of deploying a validation model with anticipated configurational changes and actual deviations may be novel.

1. 1. 1. 1. Unanswered Questions:
         2. How does this method handle complex AI models with high-dimensional data inputs?

This article does not provide details on the scalability and performance of the method when applied to complex AI models with large amounts of data.

1. 1. 1. 1. What are the potential limitations or constraints of deploying the validation model on different types of devices?

The article does not address the compatibility and resource requirements of deploying the validation model on various devices with different hardware configurations.

Original Abstract Submitted

a method for validating a trained artificial intelligence (ai) model on a device is provided. the method includes deploying a validation model generated by applying a plurality of anticipated configurational changes associated with the trained ai model requiring validation. further, the method includes providing input data to each of the validation model and the trained ai model for receiving an output from each of the validation model and the trained ai model, wherein the output of the validation model is further based on one or more actual configurational deviations that occurred during training of the trained ai model since deployment of the trained ai model on the device. furthermore, the method includes combining the output of each of the validation model and the trained ai model to validate the trained ai model.