This inventor holds 1 USPTO granted patent and 1 EPO patent. Top assignee: Gdm Holding LLC. Active years: 2026.
Company Filing History:
Years Active: 2026
Title: Jean-Baptiste Regli: Innovator in Neural Network Training
Introduction
Jean-Baptiste Regli is a prominent inventor based in London, GB. He has made significant contributions to the field of artificial intelligence, particularly in the development of methods for training neural networks. His innovative approach has garnered attention in the tech community.
Latest Patents
Jean-Baptiste Regli holds a patent for a method titled "Semi-supervised keypoint based models." This invention describes a technique for training a neural network to predict keypoints of unseen objects using a training data set that includes both labeled and unlabeled training data. The method involves receiving a training data set comprising synchronized images of objects from various viewpoints, with some images labeled with ground-truth keypoints while others remain unlabeled. The neural network is trained by updating its parameters to minimize a loss function that combines both supervised and unsupervised loss functions.
Career Highlights
Jean-Baptiste Regli is currently associated with GDM Holding LLC, where he applies his expertise in neural networks and machine learning. His work focuses on enhancing the capabilities of artificial intelligence systems through innovative training methods.
Collaborations
He collaborates with notable colleagues, including Mel Vecerik and Jonathan Karl Scholz, who contribute to his research and development efforts.
Conclusion
Jean-Baptiste Regli's contributions to neural network training exemplify the innovative spirit of modern inventors. His work continues to influence advancements in artificial intelligence and machine learning.