Data Scientist

Classifying inventory using machine learning approach.
• Development of Biomerieux’s Global Supply Chain Control Tower to provide Visibility, Collaboration, Alerts, and Control of data.

Technologies used :|
- Python, TensorFlow, Keras, Sickit-learn, Pandas, Numpy, SQL

This project took place in the LIRIS laboratory (CNRS) in Ecole Centrale de Lyon.

Project : implementing a Deep Multi-Object Tracker for an all-in-one vision model

In this project, we aim to investigate computer vision methods for perception and deep understanding of the scene to enable AI empowered general purpose flexible and adaptable robotic systems for dexterous manipulation of objects. Specifically, given a scene observed by a robot, we aim to develop a general purpose “all-in-one” computer vision model for various tasks in scene understanding, e.g., detecting the objects of interest, segmenting their instances, estimating their pose, performing their tracking and further predicting one or more grasp locations for the latter stage robotic effective grasping.

This is a longstanding research problem in computer vision with applications in robotics and autonomous driving.

Key Words:
- Python, TensorFlow, OpenCV
- Image processing
- Object Detection
- Deep Neural Network
- Git
- Computer Vision
- Artficial Intelligence