Mohammad Noorchenarboo

Teaching 15 graduate-level Deep Learning courses (≈450 enrollments) — composite score 4.90/5.00, +0.27 above college average.

• Architectures covered: CNN, RNN/LSTM, Transformer, Vision Transformer, Diffusion Models, GANs
• Large Language Models (BERT, GPT) — fine-tuning, RAG, prompt engineering, and deployment pipelines
• Courses: Data Science & ML · ML Optimization Strategies · TensorFlow & Keras · Deep Learning with TensorFlow & Keras
• Integrated XAI methods (SHAP, LIME); mentored capstone projects on real-world NLP & GenAI applications

ML & LLM pipelines for clinical prediction on 180K+ multimodal EHR records across 3 hospitals.

• Benchmarked 5 text-encoding strategies (TF-IDF, ClinicalBERT, Sentence-BERT) — Sentence-BERT reduced prediction error by 16%; best model (XGBoost/LightGBM) achieved MAE=31.8 min
• Compressed ClinicalBERT (436 MB) by 99.25% via knowledge distillation + INT8/ONNX quantization — achieving 43.7× faster inference at statistically equivalent accuracy
• Deployed RAG systems and LLM-based clinical NLP on GPU-accelerated HPC with end-to-end MLOps/CI-CD pipelines
• Applied SHAP, LIME, and attention-based XAI with fairness & bias analysis across patient subgroups

Context-aware XAI framework for anomaly detection & deep learning forecasting on smart-meter time-series.

• Developed XAI framework replacing random SHAP baselines with cosine-similarity-matched windows — 38% average reduction in explanation variability across 10 DL architectures (LSTM, GRU, TCN, WaveNet, TFT)
• Benchmarked 20+ forecasting architectures including Temporal Fusion Transformer and 1D-CNN across 250+ hyperparameter combinations
• End-to-end ML pipelines with SQL databases, R Shiny & Flask dashboards; 3 peer-reviewed publications

Supporting undergraduate and graduate courses in software engineering, data science, and machine learning.

• DATASCI 3000A: Introduction to Machine Learning (Sep–Dec 2025)
• Software Project & Process Management (Sep–Dec 2024)
• SE2250B: Software Construction (Jan–Apr 2024)
• Programming Fundamentals for Engineers (Sep 2022 – Jan 2023)

Built data pipelines and applied ML for large-scale genomic and clinical trial data analysis.

• Data pipelines and QC workflows for large-scale genomic and clinical trial datasets
• Multi-omics ML models integrated into interactive R Shiny applications
• Genotype–phenotype association studies using Python, R, and PLINK

Predictive ML and risk modeling across banking, insurance, and retail — 500+ statistical consulting projects.

• Delivered ML solutions for credit scoring, fraud detection, churn modeling, customer segmentation, and demand forecasting
• Led A/B testing, power analysis, meta-analysis, and survey analytics in R and Python across diverse industries
• Designed statistical analysis plans and experimental designs; automated reporting workflows

Built statistical programs for biomedical data analysis in rare disease research.

• Statistical software for rare disease biomedical datasets ensuring data integrity
• Data visualizations and accessible statistical summaries for interdisciplinary teams

AI and healthcare analytics — deep learning, transformers, multimodal fusion, and explainable AI.

• Transformer and multimodal deep learning models for clinical prediction and surgical efficiency
• Explainable AI (SHAP, LIME, attention) for healthcare model transparency
• Peer-reviewed publications in collaboration with LHSC clinical partners
• Danny Ho Software Engineering Scholarship ($10,000) — May 2025
• Graduate Scholarship in Engineering and Science ($1,000) — 2026

Advanced statistical modeling for clinical trials, longitudinal studies, and high-dimensional genomic data.

• Survival analysis, mixed-effects models, and causal inference methods
• Genomic and high-dimensional data analysis using R and Python

Optimization, simulation, and data-driven methods for supply chain and operational efficiency.

• Supply chain optimization and resource allocation modeling
• Simulation-based decision-making systems for industrial processes

Foundations in probability theory, statistical modeling, experimental design, and statistical computing.

• Probability theory, hypothesis testing, and statistical modeling
• R programming, survey design, and experimental study methods