Transcriptomic cell type structures in vivo neuronal activity across multiple time scales.
Cell Reports, April 2023.
Mehdi Azabou - ML PhD Student @ Georgia Tech
I am actively working on developing methods for self-supervised representation learning for different modalities, and researching new models to learn from neural activity and behavior.
| May 2023 | I am interning at IBM Research this summer. I will be at the IBM Thomas J. Watson Research Center in New York. | |
| Apr 2023 | Half-Hop is accepted at ICML 2023 🎉. More details coming soon. | |
| Apr 2023 | Our paper on identifying cell type from in vivo neuronal activity was published in Cell Reports [Link]. | |
| Mar 2023 | Check out our latest behavior representation learning model BAMS which ranks first 🥇 on the MABe 2022 benchmark [Project page]. |
I am a third-year Machine Learning Ph.D. student advised by Dr. Eva L. Dyer. My main areas of interest are 🤖 Deep Learning and 🧠 Computational Neuroscience.
My research focuses on the development of new methods for representation learning. I am particularly interested in expanding the use of these tools to novel domains where the structure of the data can be complex and obscured. Through the development of new approaches for analyzing and interpreting complex modalities, I aim to make an impact in our understanding of the brain, and biological intelligence, and to contribute new tools that facilitate new scientific discoveries.
I am currently working on developing methods for learning representations of neural activity, behavior, and graphs, with the goal of improving our understanding of the brain. If you are interested in collaborating, feel free to reach out!
I love coding and learning new things. I am an enthusiast for dynamic and interactive visualizations that can provide insights into complex data and enable new ways of thinking. I received a MS in Engineering from CentraleSupélec, France in 2019 and a MS in Computer Science from Georgia Tech in 2020.
- Ph.D. in Machine Learning, Georgia Tech 🇺🇸, Current
- M.S. in Computer Science, Georgia Tech 🇺🇸, 2020
- M.S. in Engineering, CentraleSupélec 🇫🇷, 2019
- AI Research Scientist Intern @ IBM Research, 2023
- Deep Learning Intern @ Parrot Drones, 2019
- Machine Learning & Computer Vision Intern @ Cleed, 2018
- Co-Instructor for the representation learning hands-on session during the Caltech/Chen Institute’s Data Science and AI for Neuroscience Summer School, Pasadena, California, 2022.
-
Content Developer for the Python bootcamp session for the DL@MBL: Deep Learning for Microscopy Image Analysis course at Marine Biological Laboratory, Woods Hole, Massachusetts, 2021.Materials
-
Content Developer for BMED 6517 Machine Learning in Biosciences at Georgia Tech, 2021.
-
Teaching Assistant for CS 4261 Mobile applications and Services at Georgia Tech, Spring 2019.
- I have served as a reviewer for notable conferences and journals:
- International Conference on Machine Learning, ICML '23
- Computer Vision and Pattern Recognition, CVPR '23
- Neural Information Processing Systems, NeurIPS '21/22
- Learning on Graphs Conference, LOG '22
- Artificial Intelligence and Statistics, AISTATS '21
- IEEE Transactions on Knowledge and Data Engineering
- Cell Patterns, 2022
- Sub-reviewer for Neuron, 2021
- I was privileged to work with and mentor a group of outstanding students at Georgia Tech:
- Vinam Arora, Master's in ECE, 2023
- Venkataramana Ganesh, Master's in CS, 2022-2023
- Michael Mendelson, Undergrad in BME, 2021-2023
- Santosh Nachimuthu, Undergrad in BME, 2023
- Carolina Urzay, Undergrad in BME, 2021-2022
- Zijing Wu, Undergrad in CS / Math, 2020-2021
- Main Programming Language: Python.
- ML frameworks: PyTorch, PyG, jax.
- Favorite tools: Bokeh, Flask, Docker, TensorBoard, raytune.
- Favorite tools: Illustrator, After Effects
- Designed a logo (with colorful variants) for the Neural Data Science (NeRDS) Lab at Georgia Tech.
- Designed this website using Bulma elements, icons from Font Awesome, and netlify for hosting. Javascript written with the help of ChatGPT and art generated using DALL·E 2. Code can be found here.
