MICROSOFT TECHNOLOGY LICENSING, LLC (20240256922). FAST ADAPTATION FOR DEEP LEARNING APPLICATION THROUGH BACKPROPAGATION simplified abstract
Contents
FAST ADAPTATION FOR DEEP LEARNING APPLICATION THROUGH BACKPROPAGATION
Organization Name
MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor(s)
Ganesh Ananthanarayanan of Sammamish WA (US)
Yuanchao Shu of Kirkland WA (US)
FAST ADAPTATION FOR DEEP LEARNING APPLICATION THROUGH BACKPROPAGATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240256922 titled 'FAST ADAPTATION FOR DEEP LEARNING APPLICATION THROUGH BACKPROPAGATION
Simplified Explanation: The patent application describes a method for dynamically adjusting configuration settings for capturing content as input data for inferencing in a 5G telecommunication network using a deep neural network.
Key Features and Innovation:
- Dynamically adapting configuration settings for capturing content as input data for inferencing in a 5G network
- Utilizing a deep neural network for inferencing
- Determining gradients to update configuration settings based on changes in inference data
- Combining input-configuration gradient and inference-input gradient for optimization
Potential Applications: This technology can be applied in various industries such as telecommunications, artificial intelligence, edge computing, and data analytics.
Problems Solved: This technology addresses the need for efficient and optimized configuration settings for capturing content as input data for inferencing in a 5G network.
Benefits:
- Improved accuracy and efficiency in inferencing processes
- Real-time adaptation to changing input data
- Enhanced performance of deep neural networks in edge computing environments
Commercial Applications: The technology can be used in telecommunications networks, AI-powered applications, edge computing solutions, and data analytics platforms to enhance performance and optimize inferencing processes.
Prior Art: Readers can explore prior research on dynamic configuration settings for inferencing in 5G networks, deep neural networks, and edge computing technologies.
Frequently Updated Research: Stay updated on the latest advancements in dynamic configuration settings for inferencing in 5G networks, deep neural networks, and edge computing by following relevant research publications and conferences.
Questions about Dynamic Configuration Settings for Inferencing in 5G Networks: 1. How does this technology improve the efficiency of inferencing processes in 5G networks? 2. What are the key factors to consider when dynamically adapting configuration settings for capturing content as input data for inferencing in a 5G network?
Original Abstract Submitted
systems and methods are provided for dynamically adapting configuration setting associated with capturing content as input data for inferencing in the multi-access edge computing in a 5g telecommunication network. the inferencing is based on a use of a deep neural network. in particular, the method includes determining a gradient of a change in inference data over a change in configuration setting for capturing input data (the inference-configuration gradient). the method further updates the configuration setting based on the gradient of a change in inference data over a change in the configuration setting. the inference-configuration gradient is based on a combination of an input-configuration gradient and an inference-input gradient. the input-configuration gradient indicates a change in input data as the configuration setting value changes. the inference-input gradient indicates, as a saliency of the deep neural network, a change in inference result of the input data as the input data changes.