Company Filing History:
Years Active: 2025
Title: Ferdous Pervej: Innovator in Machine Learning for Vehicular Networks
Introduction
Ferdous Pervej is a notable inventor based in Raleigh, NC, specializing in advanced machine learning techniques. His work focuses on enhancing communication and computation in vehicular networks, contributing significantly to the field of distributed machine learning.
Latest Patents
Ferdous holds a patent for "Communication and computation aware distributed machine learning for vehicular networks." This innovative method involves training a global machine learning model using a learning server and a set of vehicle agents connected to roadside units (RSUs). The process includes selecting agents, associating them with RSUs based on proximity, and transmitting training data along with deadlines. Agents train models locally, which are then aggregated through RSUs to refine the global model to the desired precision.
Career Highlights
Ferdous Pervej is currently employed at Mitsubishi Electric Research Laboratories, Inc., where he applies his expertise in machine learning and vehicular networks. His contributions to the field have been recognized through his patent and ongoing research efforts.
Collaborations
Ferdous has collaborated with esteemed colleagues such as Jianlin Guo and Kyeong-Jin Kim, further enhancing the impact of his work in the research community.
Conclusion
Ferdous Pervej's innovative approach to machine learning in vehicular networks exemplifies the potential of technology to improve communication and computation. His contributions are paving the way for advancements in this critical area of research.