This inventor holds 2 USPTO granted patents and 2 EPO patents. Top assignee: Here Global B.v.. Active years: 2020-2022.
Company Filing History:
Years Active: 2020-2022
Title: Innovations of Vladimir Shestak
Introduction
Vladimir Shestak is an accomplished inventor based in Chicago, IL (US). He has made significant contributions to the field of machine learning and in-vehicle technology. With a total of 2 patents, his work focuses on enhancing data selection and feature detection models.
Latest Patents
Vladimir's latest patents include a method, apparatus, and system for in-vehicle data selection for feature detection model creation and maintenance. This innovative approach involves selecting training observations for machine learning models by determining distributions of features in both training data and candidate pools. The selected observations are then annotated and added to the training data set for model training.
Another notable patent is the method, apparatus, and system for dynamic adaptation of an in-vehicle feature detector. This invention allows for the embedding of feature detection models and precomputed weights into map data. It enables the adaptation of in-vehicle feature detectors based on geographic areas, enhancing their ability to process sensor data and detect features effectively.
Career Highlights
Vladimir Shestak is currently employed at Here Global B.V., where he continues to innovate in the field of automotive technology. His work is pivotal in advancing the capabilities of in-vehicle systems, making them more responsive and intelligent.
Collaborations
Vladimir collaborates with talented individuals such as Nicholas Dronen and Stephen O'Hara. Their combined expertise contributes to the development of cutting-edge technologies in the automotive sector.
Conclusion
Vladimir Shestak's contributions to machine learning and in-vehicle technology are noteworthy. His patents reflect a commitment to innovation and improvement in automotive systems. His work continues to influence the future of in-vehicle feature detection and data selection methodologies.