MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202544112798 A) filed by Nokia Solutions And Networks Oy on November 17, 2025, for Apparatus, Method, And System Forproviding Machine Learning Dynamic Complexity Modeling For Adaptive Data Sharing In Simultaneous Localization And Mapping.
Inventors include Jacky Cao; and Maryam Sabzevari.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: ABSTRACT APPARATUS, METHOD, AND SYSTEM FOR PROVIDING MACHINE LEARNING DYNAMIC COMPLEXITY MODELING FOR ADAPTIVE DATA SHARING IN SIMULTANEOUS LOCALIZATION AND MAPPING 5 An approach is provided for machine learning (ML) dynamic complexity modeling for adaptive data sharing in simultaneous localization and mapping (SLAM). The approach involves, for example, receiving an output of a ML model that performs a keypoints extraction task on image 10 frame data and has an adaptive model complexity capable of an early exit before a final layer of the machine learning model. The approach also involves determining a temporal loss based on differences between features detected in two or more temporally successive image frames, and determining performance metrics of a communication network for the transmitting the output to a server device. The approach further involves determining a loss metric based on the temporal loss 15 and/or the performance metrics, and initiating the early exit of the machine learning model based on the loss metric
Disclaimer: Curated by HT Syndication.
