US Patent Application 17998323. End-to-End Deep Neural Network Adaptation for Edge Computing simplified abstract
Contents
End-to-End Deep Neural Network Adaptation for Edge Computing
Organization Name
Inventor(s)
Jibing Wang of San Jose CA (US)
Erik Richard Stauffer of Sunnyvale CA (US)
End-to-End Deep Neural Network Adaptation for Edge Computing - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 17998323 Titled 'End-to-End Deep Neural Network Adaptation for Edge Computing'
Simplified Explanation
This abstract describes techniques and apparatuses for adapting a machine learning configuration for processing communications in an end-to-end (E2E) communication system. The system involves a network entity, user equipment (UE), base station, and an edge compute server (ECS). Initially, the network entity directs the UE and base station to form a deep neural network (DNN) based on a specific machine learning configuration. However, if there is a change in the participation mode of the ECS, the network entity determines to update the machine learning configuration. It identifies a new configuration and directs either the UE or the base station to update the DNN using this new configuration.
Original Abstract Submitted
Techniques and apparatuses are described for adapting an end-to-end, E2E, machine-learning, ML, configuration for processing communications transferred through an E2E communication. A network entity directs a user equipment (UE) and a base station participating in the E2E communication to implement the E2E communication by forming at least a portion of an E2E deep neural network, DNN, based on a first E2E ML configuration. The network entity determines to update the first E2E ML configuration based on a change in a participation mode of an edge compute server (ECS) in the E2E communication. The network entity identifies a second E2E ML configuration based on the change in participation mode and directs the UE or the base station to update the portion of the E2E DNN using the second E2E ML configuration.
