Soroosh Shahtalebi - Senior Machine Learning Scientist

About Me

As a Senior Machine Learning Scientist, I specialize in Machine Learning, Generative AI, and Statistical Signal Processing. My professional journey has been marked by a deep commitment to advancing the field of AI through innovative solutions in Structure from Motion, 3D Reconstruction, and Computer Vision. With proficient skills in Python programming, I have developed and deployed advanced models on platforms such as Google Cloud Platform and Microsoft Azure, utilizing best practices in MLOps, Kubernetes, and continuous integration and delivery (CI/CD) processes. This website showcases my journey, contributions, and the continuous pursuit of knowledge in the ever-evolving landscape of technology.

Experience

Unity Technologies - Senior Machine Learning Engineer
- Developed Generative AI solutions for materials, textures, and human body.
- Conducted research on Out-of-Distribution Generalization using synthetic data.
- Worked on the development of 3D object and scene reconstruction pipelines.
- Involved in the productionization and deployment of ML models at large-scale over GCP and Microsoft Azure.
University of Toronto and Vector Institute for Artificial Intelligence - Postdoctoral Research Fellow
Project: Theory of Domain Generalization applied in Healthcare
Mila University of Montreal - Postdoctoral Research Fellow
Project: Theoretical perspectives on Out-of-Distribution Generalization
MathWorks - Part-time Consultant
Provided consultations to improve the Wavelet Toolbox of MATLAB software.
Ubico Labs - Part-time Technical Consultant
Advised on integrating ML into automated mailing systems.
Hooshmand Afzar Pars - CEO and Founder
Specialized in the design and production of Bio-feedback and Neuro-feedback devices.

Education

PhD in Information Systems Engineering
Concordia University, Montreal, QC, Canada (2016–2020)
With distinction, Outstanding grade. Project on Effective Application of Data-driven Learning Models for Assistive Technologies and Brain-computer Interfaces.
M.Sc. in Biomedical Engineering (minor in Bio-electrics)
K. N. Toosi University of Technology, Tehran, Iran (2013–2015)
With distinction. Project on Design and implementation of the processing and controlling circuit board of a blood cell counting machine.
Bachelor's in Electrical Engineering (major in Telecommunication)
Yazd University, Yazd, Iran (2009–2013)
Project on Design and production of a planar goniometer for joint angle measurement.

Selected Publications

NoiseNet; Self-augmenting Noisy Neural Architectures Generalize to Unseen Covariate Shifts - S. Shahtalebi and F. Rudzicz, Submitted (2022).
Out-of-Distribution Failure through the Lens of Labeling Mechanisms: An Information Theoretic Approach - S. Shahtalebi, Z. Zhu, and F. Rudzicz, ICML Workshop on Spurious Correlations Invariance and Stability (2022).
OOD-Probe: A Neural Interpretation of Out-of-Domain Generalization - Z. Zhu, S. Shahtalebi, and F. Rudzicz, ICML Workshop on Spurious Correlations Invariance and Stability (2022).
Predicting Fine-Tuning Performance with Probing - Z. Zhu, S. Shahtalebi, and F. Rudzicz, EMNLP (2022).
EDT: A Remedy for Distributional Shifts through Domain Translation - J.C. Gagnon Audet, S. Shahtalebi, F. Rudzicz, and I. Rish, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2022), Singapore.
SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization - S. Shahtalebi, J.C. Gagnon-Audet, T. Laleh, M. Faramarzi, K. Ahuja, and I. Rish, ICML Workshop on Uncertainty and Robustness in Deep Learning (2021).
A Deep Explainable Artificial Intelligent Framework for Neurological Disorders Discrimination - S. Shahtalebi, S. F. Atashzar, R. V. Patel, M. S. Jog, and A. Mohammadi, Scientific Reports, Nature Publishing Group (2021).
PHTNet: Characterization and Deep Mining of Involuntary Pathological Hand Tremor using Recurrent Neural Network Models - S. Shahtalebi, S. F. Atashzar, O. Samotus, R. V. Patel, M. S. Jog, and A. Mohammadi, Scientific Reports, Nature Publishing Group (2020).
HMFP-DBRNN: Real-time Hand Motion Filtering and Prediction via Deep Bidirectional RNN - S. Shahtalebi, S.F. Atashzar, R.V. Patel, and A. Mohammadi, IEEE Robotics and Automation Letters (2019).

Talks

Founder and Organizer of the "Ethical AI" Reading Group - An initiative to foster discussions on the ethical aspects of artificial intelligence.
PhD Representative at Council Meetings, Concordia University Canada - Participated in departmental council meetings, contributing to discussions and decision-making (2018-2020).
Reviewer and Contributor at Notable Conferences - Acted as a reviewer and contributor to discussions in various prestigious conferences such as MAIS, ICASSP, EMBC, SMC, and GlobalSIP.

Awards