Héloïse Barbier
About Héloïse Barbier
Héloïse Barbier is a Machine Learning Engineer at VergeSense, where she has worked since 2021 in the San Francisco Bay Area. She specializes in instance segmentation using PyTorch and develops object detection solutions for edge sensors using TensorFlow.
Work at VergeSense
Héloïse Barbier has been employed as a Machine Learning Engineer at VergeSense since 2021. In this role, she focuses on developing advanced machine learning models and solutions, particularly in the area of instance segmentation. Her work contributes to the company's efforts in enhancing object detection capabilities for edge sensors, which are critical for various applications in the field of smart building technology.
Education and Expertise
Héloïse Barbier has a strong educational background in engineering and technology. She earned a Master of Science in Electrical Engineering from the Illinois Institute of Technology from 2019 to 2020. Prior to that, she completed another Master of Science in Electrical and Computer Engineering at Ecole nationale supérieure de l'Electronique et de ses Applications from 2017 to 2020. Her foundational studies include a three-year program in Mathematics, Physics, and Engineering Sciences at Saliège Campus, and a Baccalauréat in scientific studies from Lycée Pierre De Fermat.
Background
Héloïse Barbier's early education included rigorous training in scientific disciplines. She attended Lycée Pierre De Fermat, where she completed her Baccalauréat from 2011 to 2014. Following this, she pursued advanced studies in Mathematics, Physics, and Engineering Sciences at Saliège Campus from 2014 to 2017. Her international experience includes an internship at MECAPREC in 2018, where she gained practical skills in the field of engineering.
Technical Skills and Specializations
Héloïse Barbier specializes in instance segmentation using PyTorch, a critical area in the field of computer vision. She also develops object detection solutions for edge sensors utilizing TensorFlow. Her technical skills include improving training efficiency, as demonstrated by her successful migration of the codebase from TensorFlow 1 to TensorFlow 2, which resulted in a 20% increase in training efficiency.