Mohammad Taha Askari

At UBC’s Data Communications Group, I conduct graduate research on probabilistic modeling and sequence design for communication systems with memory and nonlinear dynamics. I developed an analytical low-pass filter model to characterize how probabilistic shaping interacts with nonlinear channels and used it to guide interpretable system-level design.

I also proposed a sequence selection algorithm that improves robustness to nonlinear interference by exploiting temporal dependencies, and designed a Bayesian carrier phase recovery method that incorporates prior distributions for improved low-SNR performance. My current work explores end-to-end learning approaches using neural sequence models for joint distribution learning in communication systems.

At Nokia Bell Labs, I focused on machine learning research for sequence modeling and joint distribution learning. I designed and implemented Neural Probabilistic Shaping (NPS), an autoregressive neural framework trained end-to-end using differentiable sampling (e.g., Gumbel-Softmax) and differentiable channel models.

I built a scalable training and evaluation pipeline in Python, ran extensive experiments on multi-dimensional system settings, and benchmarked learned models against classical baselines and heuristic methods. This work emphasized model design, optimization, and empirical validation of neural sequence models for communication systems with memory.

At Roche Canada, I worked in an applied ML and software engineering environment on large-scale sequencing data. I built pipelines for feature extraction, dataset generation, and neural network training to support anomaly detection workflows.

I developed and optimized weakly supervised deep learning models, including a multi-label architecture for multi-class anomaly detection and segmentation. I also integrated model evaluation, interpretability, and computational complexity analysis to support iterative improvement.